# Retrieval Augmented Generation (RAG)

A language-generation technique that retrieves relevant information from an external non-parametric memory and uses it as context for a pretrained model.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Why Trust Your Agent? Empirical Security Gains from TRiSM-Guided Agentic Workflows in Healthcare

DevFeed: [Why Trust Your Agent? Empirical Security Gains from TRiSM-Guided Agentic Workflows in Healthcare](<https://devfeed.tech/articles/why-trust-your-agent-empirical-security-gains-from-trism-guided-agentic-workflows-in-healthcare-145354.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.28666>)

Author: Liam Kearns

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [LLM security](<https://devfeed.tech/topics/llm-security.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [least privilege](<https://devfeed.tech/topics/least-privilege.md>), [Security](<https://devfeed.tech/topics/security.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-trust](<https://devfeed.tech/tags/ai-trust.md>), [attack](<https://devfeed.tech/tags/attack.md>), [automation](<https://devfeed.tech/tags/automation.md>), [breaches](<https://devfeed.tech/tags/breaches.md>), [claude-haiku-4-5](<https://devfeed.tech/tags/claude-haiku-4-5.md>), [client](<https://devfeed.tech/tags/client.md>), [construction](<https://devfeed.tech/tags/construction.md>), [covid-19](<https://devfeed.tech/tags/covid-19.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [data](<https://devfeed.tech/tags/data.md>), [diagnosis](<https://devfeed.tech/tags/diagnosis.md>), [disclosure](<https://devfeed.tech/tags/disclosure.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [generation](<https://devfeed.tech/tags/generation.md>), [healthcare](<https://devfeed.tech/tags/healthcare.md>), [security](<https://devfeed.tech/tags/security.md>), [trust](<https://devfeed.tech/tags/trust.md>)

### AI overview

In a medical report-generation application tested with five LLMs, a TRiSM-guided workflow reduced attack success for RAG poisoning (31% to 10%) and data-field injection (42% to 25%), eliminated client-side network injection by construction, and increased report accuracy from 72.5% to 86.5%. In an exploratory grouping, attacks aimed beyond the reporting task, including data disclosure and tool abuse, fell from 21.7% to 2.5%, with no patient records disclosed under the redesign. However, attacks that changed the Covid-19 diagnosis remained effective, making up 32 of 35 successful attacks against the redesign. The findings suggest least privilege limits what injections can reach but cannot ensure the model resists injected content within its task; clinical outputs still need independent verification. No tested model resisted all three attack vectors.

### Source excerpt

arXiv:2606.28666v2 Announce Type: replace-cross Abstract: Agent-based AI has enabled the automation of tasks by exposing application tools and resources to large language models (LLMs). However, to improve scope and accuracy, agents are often given access rights that exceed those of ordinary users, introducing significant security risks and potential regulatory breaches. This paper applies the AI Trust, Risk, and Security Management (TRiSM) framework to a medical report-generation application to demonstrate how an insecure baseline workflow can be transformed into a security-conscious agentic workflow. Both designs were evaluated with five LLMs (Claude Haiku 4.5, GPT-4.1-nano, GPT-4.1-mini, GPT-5.4-mini and Gemini 2.5 Flash) across 800 report generations and 500 attack trials covering RAG poisoning, data-field injection and client-side network injection. The redesign reduced attack success from 31% to 10% for RAG poisoning and from 42% to 25% for data-field injection (McNemar p < 0.001 for both), removed network injection by construction, and raised report accuracy from 72.5% to 86.5%. In an exploratory post-hoc grouping by attack goal, success against attacks aimed outside the report task, such as data disclosure and tool abuse, fell from 21.7% to 2.5% and no patient record was disclosed under the redesign. Attacks altering the reported Covid-19 diagnosis remained effective, accounting for 32 of the 35 successful attacks against the redesign. Least-privilege architecture limits what an injection can reach, but not whether a model follows injected content within its task, so clinical outputs need verification independent of the LLM. No model resisted all three attack vectors, so model selection cannot substitute for secure workflow design.

## Decoupled Knowledge Retrieval and Compact Memory Enable Reliable Lifelong Model Editing

DevFeed: [Decoupled Knowledge Retrieval and Compact Memory Enable Reliable Lifelong Model Editing](<https://devfeed.tech/articles/decoupled-knowledge-retrieval-and-compact-memory-enable-reliable-lifelong-model-editing-145596.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25861>)

Author: Yue Che, Jingze Wang, Chen Guoyi, Yujie Wu, Xuming Ran, Mingkun Xu

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [AI-driven information retrieval](<https://devfeed.tech/topics/ai-driven-information-retrieval.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>)

Tags: [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [memory](<https://devfeed.tech/tags/memory.md>), [model](<https://devfeed.tech/tags/model.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>)

### AI overview

BiSpace addresses growing storage needs and declining retrieval performance in memory-based lifelong model editing while leaving the base LLM parameters untouched. It separates retrieval and injection across representation spaces: queries locate edits in an external semantic space, and sparse, storage-efficient updates inject the relevant knowledge into the model's internal representation space. The abstract reports that BiSpace reduces storage per entry to about 10.2% of the original, remains resilient through edit sequences of up to 16K edits, and improves Overall Performance by more than 23% over existing methods on a more challenging benchmark.

### Source excerpt

arXiv:2611.25861v1 Announce Type: new Abstract: Lifelong model editing requires continuously incorporating new facts into deployed large language models (LLMs) without expensive retraining or compromising existing capabilities. Memory-based editors offer an appealing solution by keeping the base parameters untouched, yet their practical use is hindered by linearly growing storage requirements and deteriorating retrieval performance as edits accumulate. To tackle these problems, we introduce BiSpace, a lifelong model editing framework that decouples memory retrieval from knowledge injection across two distinct representation spaces. BiSpace routes queries and identifies relevant edits in an external semantic space, while injecting the corresponding knowledge into the internal representation space of the LLM through sparse and storage-efficient updates. Extensive experiments show that BiSpace shrinks each entry's storage to only about 10.2% of the original and shows strong resilience to long edit sequences of up to 16K edits. On a more challenging benchmark, BiSpace further improves Overall Performance by more than 23% over existing methods. These results advance memory-based editing toward reliable long-term model maintenance at scale.

## STARK: Moving towards Personalized Agents That Truly Learn and Remember

DevFeed: [STARK: Moving towards Personalized Agents That Truly Learn and Remember](<https://devfeed.tech/articles/stark-moving-towards-personalized-agents-that-truly-learn-and-remember-145574.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25705>)

Author: Aryan Jain, Abhishek Jha, Anish Nediyanchath, Promod Yenigalla

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>)

Tags: [agentic-systems](<https://devfeed.tech/tags/agentic-systems.md>), [cold-start](<https://devfeed.tech/tags/cold-start.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [graph](<https://devfeed.tech/tags/graph.md>), [inference](<https://devfeed.tech/tags/inference.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [llm](<https://devfeed.tech/tags/llm.md>), [memory-architecture](<https://devfeed.tech/tags/memory-architecture.md>), [rouge](<https://devfeed.tech/tags/rouge.md>), [sparsity](<https://devfeed.tech/tags/sparsity.md>)

### AI overview

STARK uses two linked graphs to store long-term user memory: an Episodic Graph of temporally, causally, and semantically connected interactions, and an Insight Graph of behavioral signals supported by those events. At inference, it retrieves grounded insights directly instead of repeatedly traversing episodes. Representing events as links between insights also supports relational embeddings for transferring knowledge across users in shared contexts and inferring missing insights for cold-start users. The abstract reports gains over state of the art of 1.48 judge score on LongMemEval information extraction and 0.93 on LoCoMo open-domain questions. On LongLaMP, cross-user transfer at 5% graph sparsity improves open-ended judge scores by 0.7 points and ROUGE-L by 3.

### Source excerpt

arXiv:2611.25705v1 Announce Type: cross Abstract: Long-term memory is essential for personalized agentic systems that interact with users over long time periods, yet current architectures only capture what happened while leaving the reasoning of why it happened to be derived later by underlying LLMs.%, and silo knowledge within individual users. These events can, however, convey not only what a user experienced but also how that experience shaped their behavioral patterns. We introduce STARK, a dual-graph memory architecture which treats these events not just as nodes but also as edges between behavioral insights. STARK maintains an Episodic Graph which records interactions as temporally, causally, and semantically linked episodes; and an Insight Graph which represents LLM-extracted behavioral signals scored by how many events support them, connected by the very events that led to them. At inference, behavioral knowledge is retrieved directly from insight nodes grounded by event-as-edges, eliminating repeated episodic traversal. The event-as-edge structure also naturally enables projecting the knowledge graph into a relational embedding space where cross-user transfer becomes possible under shared contextual circumstances, allowing the system to infer missing insights for cold-start users. Evaluations show that STARK improves by 1.48 judge score on LongMemEval information extraction and 0.93 on LoCoMo open domain questions over state of the art. On the public LongLaMP abstract-generation benchmark, cross-user transfer improves open-ended judge scores by 0.7 points and ROUGE-L by 3 at 5% graph sparsity.

## From Industrial Product Documentation to Automated Digital Product Passport Generation: An Experimental Study of Large Language Models

DevFeed: [From Industrial Product Documentation to Automated Digital Product Passport Generation: An Experimental Study of Large Language Models](<https://devfeed.tech/articles/from-industrial-product-documentation-to-automated-digital-product-passport-generation-an-experimental-study-of-large-language-models-145733.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24998>)

Author: Marco Buecheler, Grant Richards, Nathan Hartman

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Databases](<https://devfeed.tech/sources/arxiv-databases.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Vectors & LLMs](<https://devfeed.tech/topics/vectors-llms.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [hybrid-search](<https://devfeed.tech/topics/hybrid-search.md>), [Factuality scoring in AI](<https://devfeed.tech/topics/factuality-scoring-in-ai.md>)

Tags: [automated](<https://devfeed.tech/tags/automated.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [digital](<https://devfeed.tech/tags/digital.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [experimental](<https://devfeed.tech/tags/experimental.md>), [generation](<https://devfeed.tech/tags/generation.md>), [industrial](<https://devfeed.tech/tags/industrial.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [passport](<https://devfeed.tech/tags/passport.md>), [product](<https://devfeed.tech/tags/product.md>), [study](<https://devfeed.tech/tags/study.md>)

### AI overview

The study tests a RAG pipeline for generating Digital Product Passports as Asset Administration Shell instances from scattered industrial documentation. It chunks documents, stores embeddings in ChromaDB, combines semantic and lexical retrieval against AAS submodel requirements, and supplies retrieved content to five LLMs. Across 4,560 executions covering 76 product-submodel combinations, 97.4% of outputs were valid JSON, but 44.9% passed full AAS validation. Deterministic scoring found mean completeness of 49.6%, conditional accuracy of 58.3%, and overall field correctness of 30.8%; an LLM judge rated the same outputs higher at 66.5%, 88.9%, and 60.4%. The abstract says four prompt-guidance levels were evaluated but does not report their comparative effects.

### Source excerpt

arXiv:2611.24998v1 Announce Type: cross Abstract: Manufacturing companies that are planning to sell certain products in the European Union (EU) will be required to provide mandatory digital product passports (DPPs). The use of DPPs is to provide standardized product information throughout multiple product life cycles in a circular economy. Required passport information, such as technical specifications, material composition, and environmental product footprint, is available in manufacturers' data sources but is scattered across different heterogeneous systems, documents, and data formats. The given paper investigates using large language models (LLMs) to automate the generation of DPPs based on the asset administration shell (AAS). A retrieval-augmented generation (RAG) approach is used to extract product information from industrial documentation and generate populated AAS instances. Product documentation is processed and divided into text chunks. The text chunks are then stored in a persistent ChromaDB vector database using vector embeddings. The retrieval process combines semantic and lexical search to identify relevant information based on standardized AAS submodel template requirements. The retrieved information is provided to five LLMs to generate structured AAS instances. The experiments cover different industrial products and AAS submodels. Four levels of prompt guidance are investigated to assess their influence on generation quality. The generated passports are evaluated against a ground truth. The experimental evaluation includes 4,560 executions across 76 product-submodel combinations. Of the generated passport outputs, 97.4% are valid JSON, while 44.9% pass the full AAS validation procedure. Under deterministic scoring, mean completeness, conditional accuracy, and overall field correctness are 49.6%, 58.3%, and 30.8%, respectively. An LLM-as-a-judge yields better scores of 66.5%, 88.9%, and 60.4% for the same outputs.

## MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems

DevFeed: [MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems](<https://devfeed.tech/articles/minteval-evaluating-memory-under-multi-target-interference-in-long-horizon-agent-systems-145334.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.18565>)

Author: Hyunji Lee, Justin Chih-Yao Chen, Joykirat Singh, Zaid Khan, Elias Stengel-Eskin, Mohit Bansal

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-frameworks](<https://devfeed.tech/tags/agent-frameworks.md>), [aggregation](<https://devfeed.tech/tags/aggregation.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [frameworks](<https://devfeed.tech/tags/frameworks.md>), [github](<https://devfeed.tech/tags/github.md>), [horizon](<https://devfeed.tech/tags/horizon.md>), [llms](<https://devfeed.tech/tags/llms.md>), [long-context](<https://devfeed.tech/tags/long-context.md>), [long-context-llms](<https://devfeed.tech/tags/long-context-llms.md>), [memory](<https://devfeed.tech/tags/memory.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [recall](<https://devfeed.tech/tags/recall.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [revisions](<https://devfeed.tech/tags/revisions.md>), [robustness](<https://devfeed.tech/tags/robustness.md>), [state](<https://devfeed.tech/tags/state.md>), [tasks](<https://devfeed.tech/tags/tasks.md>)

### AI overview

MINTEval tests how seven systems--including long-context LLMs, RAG, and memory-augmented agents--handle evolving, interference-heavy information. Its 15.6k question-answer pairs span four domains and contexts averaging 138.8k tokens, up to 1.8M. Tasks test retrieval of a single target and aggregation across multiple pieces of evidence. Average accuracy was 27.9%, with multi-evidence reasoning especially difficult. The authors identify retrieval and memory construction as primary limitations; systems also struggled with earlier facts revised or disrupted by later context, and accuracy fell as intervening updates increased.

### Source excerpt

arXiv:2605.18565v3 Announce Type: replace-cross Abstract: Real-world agents operate over long and evolving horizons, where information is repeatedly updated and may interfere across memories, requiring accurate recall and aggregated reasoning over multiple pieces of information. However, existing benchmarks focus on static, independent recall and fail to capture these dynamic interactions between evolving memories. In this paper, we study how current memory-augmented agents perform in realistic, interference-heavy, long-horizon settings across diverse domains and question types. We introduce MINTEval (Long-Horizon Memory under INTerference Evaluation), a benchmark featuring (1) long, highly interconnected contexts with frequently updated information that induces substantial interference, (2) diverse domains (state tracking, multi-turn dialogue, Wikipedia revisions, and GitHub commits), enabling evaluation of domain generalization, and (3) diverse question types that assess robustness to interference, including (i) single-target recall tasks requiring retrieval of a specific target from long contexts, and (ii) multi-target aggregation tasks requiring reasoning over multiple relevant pieces of information. Overall, MINTEval has 15.6k question-answering pairs over long-horizon contexts averaging 138.8k tokens and extending up to 1.8M tokens per instance. We evaluate 7 representative systems, including vanilla long-context LLMs, RAG, and memory-augmented agent frameworks. Across all systems, we observe consistently low performance (avg. 27.9% accuracy), especially on questions requiring aggregated reasoning over multiple pieces of evidence. Our analysis shows that performance is primarily limited by retrieval and memory construction. Furthermore, current memory systems struggle to recall and reason over earlier facts that are revised or interfered with by subsequent context, with accuracy degrading as the number of intervening updates increases.

## AutoRAGBench: A Benchmark for LLM Agents Automating RAG System Development

DevFeed: [AutoRAGBench: A Benchmark for LLM Agents Automating RAG System Development](<https://devfeed.tech/articles/autoragbench-a-benchmark-for-llm-agents-automating-rag-system-development-145541.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25582>)

Author: Hang Zhang, Yuzhi Pan, Ziyao Zhong, Chaokun Wang, Shuo Cao, Zeyu Huang, Yue Xue, Fang Niu, Bofan Xie, Guanchen Ge, Zecheng Li, Leqi Zheng, Ziyang Liu, Wei Wang, Miao Gu

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-agents](<https://devfeed.tech/tags/llm-agents.md>), [rag](<https://devfeed.tech/tags/rag.md>), [system-development](<https://devfeed.tech/tags/system-development.md>), [systems](<https://devfeed.tech/tags/systems.md>)

### AI overview

AutoRAGBench evaluates whether LLM agents can build and improve retrieval-augmented generation systems across nine development tasks. Agents worked in an open code space without starter code or prescribed strategies, with six hours and one H800 GPU per task; they analyzed data, implemented pipelines, and refined them using experimental feedback. Across nine configurations, GPT-6.1 Sol with Codex CLI had the highest average score (56.1), compared with 44.4 for the composite Human-SOTA baseline. Starting from human-designed systems on seven tasks, it improved scores by an average of 16.6 points. These results support the benchmark's finding that agents can automate effective RAG development under the tested conditions.

### Source excerpt

arXiv:2611.25582v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) is a well-established paradigm for augmenting large language models (LLMs) with information retrieved from external corpora. However, developing effective RAG systems requires substantial engineering effort and iterative experimentation, as effective design choices vary across tasks and domains. With rapid advances in LLM agent capabilities, we ask how well these agents can autonomously build RAG systems and how effectively they can improve them through iteration. In this paper, we propose AutoRAGBench, the first benchmark to evaluate how well LLM agents develop RAG systems from scratch in an open code space. It comprises nine RAG system development tasks. For each task, agents build RAG systems from scratch without starter code or prescribed strategies, under a six-hour budget on a single H800 GPU. They analyze task data, implement RAG pipelines, and iteratively refine their designs based on experimental feedback. We evaluate nine agent configurations and analyze both the effectiveness of the resulting RAG systems and their development trajectories. GPT-6.1 Sol with Codex CLI achieves the highest average score of 56.1. The composite Human-SOTA baseline averages 44.4. These results show that LLM agents can automate effective RAG system development. When starting from a human-designed system on each of seven tasks, GPT-6.1 Sol with Codex CLI improves the score by 16.6 points on average.

## CAIMS: Scalable Cross-Array In-Memory Search

DevFeed: [CAIMS: Scalable Cross-Array In-Memory Search](<https://devfeed.tech/articles/caims-scalable-cross-array-in-memory-search-145013.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25141>)

Author: Yi-Chun Liao, Liu Liu, Ruiyang Qin, Yiran Chen, X. Sharon Hu

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [cosine similarity search](<https://devfeed.tech/topics/cosine-similarity-search.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>)

Tags: [3d-nand](<https://devfeed.tech/tags/3d-nand.md>), [accelerators](<https://devfeed.tech/tags/accelerators.md>), [array](<https://devfeed.tech/tags/array.md>), [cam](<https://devfeed.tech/tags/cam.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cs-ar](<https://devfeed.tech/tags/cs-ar.md>), [cs-et](<https://devfeed.tech/tags/cs-et.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [energy-efficiency](<https://devfeed.tech/tags/energy-efficiency.md>), [global](<https://devfeed.tech/tags/global.md>), [lightweight](<https://devfeed.tech/tags/lightweight.md>), [low-latency](<https://devfeed.tech/tags/low-latency.md>), [memory](<https://devfeed.tech/tags/memory.md>), [nand](<https://devfeed.tech/tags/nand.md>), [parallelism](<https://devfeed.tech/tags/parallelism.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [retrieval-augmented-generation](<https://devfeed.tech/tags/retrieval-augmented-generation.md>), [search](<https://devfeed.tech/tags/search.md>), [similarity-search](<https://devfeed.tech/tags/similarity-search.md>), [throughput](<https://devfeed.tech/tags/throughput.md>)

### AI overview

CAIMS addresses the challenge of combining local binary match results across multiple content-addressable memory arrays into accurate global top-k similarity results. It uses existing threshold-match functionality and offline plus online parameter selection to produce globally comparable, coarse-grained scores, then performs hierarchical reduction while transferring only selected results and necessary control signals through lightweight local peripherals. In a 3D NAND Flash model evaluated on the retrieval phase of retrieval-augmented generation, it reports up to 22.3x higher throughput and 426.6x better energy efficiency than a server-class CPU, and 10.1x higher throughput and 23.7x better energy efficiency than prior 3D NAND Flash accelerators, with comparable accuracy.

### Source excerpt

arXiv:2611.25141v1 Announce Type: cross Abstract: Search, especially top-k similarity search, plays a vital role in many applications, but its performance can be severely limited by memory access overhead. In-memory search (IMS), an alternative to CPU/GPU-based approaches, exploits massive parallelism within a content-addressable memory (CAM) array to perform search in situ and provides both low latency and high energy efficiency. However, the capacity of a single CAM array is often insufficient for modern workloads, requiring data to be distributed across multiple arrays. Deploying scalable top-k similarity search across multiple CAM arrays poses a fundamental problem that existing designs fail to address: how to accurately and efficiently reduce local binary match results to global top-k results. This work introduces CAIMS, a cross-array IMS framework that is agnostic to memory technologies and applications, enabling scalable and efficient top-k similarity search while preserving accuracy. To enable accurate top-k result reduction, CAIMS leverages the existing threshold match functionality with a combined offline and online parameter selection approach to transform local binary match results that lack globally comparable similarity information into global coarse-grained similarity scores. To further improve efficiency, CAIMS conducts hierarchical reduction and transfers only the selection results and necessary control signals with lightweight local peripherals. Implemented on a 3D NAND Flash model and demonstrated using the retrieval phase of retrieval-augmented generation, CAIMS improves throughput by up to $22.3\times/10.1\times$ and energy efficiency by $426.6\times/23.7\times$ compared to the server-class CPU baseline and prior 3D NAND Flash accelerators, respectively, while maintaining comparable accuracy.

## Democratizing Cross-Project Knowledge for Transforming Water Governance and Climate Resilience: an Agentic AI Ecosystem

DevFeed: [Democratizing Cross-Project Knowledge for Transforming Water Governance and Climate Resilience: an Agentic AI Ecosystem](<https://devfeed.tech/articles/democratizing-cross-project-knowledge-for-transforming-water-governance-and-climate-resilience-an-agentic-ai-ecosystem-145666.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26398>)

Author: Oriol Al\\\`as, Ian Palac\\'in, Iv\\'an Cester, Edgar Rubi\\'on

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-retrieval](<https://devfeed.tech/tags/agentic-retrieval.md>), [ai](<https://devfeed.tech/tags/ai.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [budget](<https://devfeed.tech/tags/budget.md>), [climate](<https://devfeed.tech/tags/climate.md>), [collections](<https://devfeed.tech/tags/collections.md>), [controller](<https://devfeed.tech/tags/controller.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [data](<https://devfeed.tech/tags/data.md>), [decision](<https://devfeed.tech/tags/decision.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [ecosystem](<https://devfeed.tech/tags/ecosystem.md>), [governance](<https://devfeed.tech/tags/governance.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [resilience](<https://devfeed.tech/tags/resilience.md>), [water](<https://devfeed.tech/tags/water.md>)

### AI overview

The paper presents an agentic retrieval system for finding evidence across EU-funded water and climate projects. It organizes documents from IMPETUS, NATALIE, and InnWater into hierarchical section trees with structured metadata, then uses separate water- and climate-domain embedding models. A ReAct-style controller allocates retrieval budget across domain collections and gathers evidence until a stopping criterion is met. In a benchmark on this corpus, the approach improved Mean Reciprocal Rank by 26.7% relative to a single-domain embedding baseline. The excerpt does not describe evaluation beyond that retrieval benchmark.

### Source excerpt

arXiv:2611.26398v1 Announce Type: cross Abstract: EU-funded projects produce extensive evidence in the form of deliverables, reports, and case studies. However, this knowledge is typically scattered across projects and document structures, making it difficult to locate relevant, contextual information when making decisions. This paper introduces an Agentic AI Ecosystem that consolidates heterogeneous project documentation into a domain-aware knowledge base and provides adaptive access through an agentic Retrieval-Augmented Generation pipeline. Documents from three EU-funded projects (IMPETUS, NATALIE, and InnWater) are reconstructed into hierarchical section trees and indexed with structured metadata. Retrieval is supported by two domain-specific embedding models fine-tuned on domain data (water and climate). On top of this knowledge base, a ReAct-style controller iteratively orchestrates retrieval actions by allocating retrieval budget across domain collections and accumulating evidence until a stopping criterion is met. In a retrieval benchmark over the corpus, the proposed approach improves Mean Reciprocal Rank by 26.7% (relative) compared to a single-domain embedding baseline, indicating more consistent retrieval of relevant evidence to support cross-project knowledge synthesis and climate-resilient decision-making.

## SPARK: Adaptive Parametric Knowledge Participation for Faithful Retrieval-Augmented Generation

DevFeed: [SPARK: Adaptive Parametric Knowledge Participation for Faithful Retrieval-Augmented Generation](<https://devfeed.tech/articles/spark-adaptive-parametric-knowledge-participation-for-faithful-retrieval-augmented-generation-145353.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.27786>)

Author: Ruochang Li, Pengcheng Huang, Zhenghao Liu, Yukun Yan, Huiyuan Xie, Yu Gu, Ge Yu, Maosong Sun

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [peft](<https://devfeed.tech/topics/peft.md>), [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [faithfulness](<https://devfeed.tech/tags/faithfulness.md>), [generation](<https://devfeed.tech/tags/generation.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [retrieval-augmented-generation](<https://devfeed.tech/tags/retrieval-augmented-generation.md>), [spark](<https://devfeed.tech/tags/spark.md>)

### AI overview

SPARK addresses conflicts between retrieved evidence and an LLM's internal knowledge by learning a lightweight policy that dynamically adjusts the contribution of feed-forward-network-mediated parametric knowledge during generation. It keeps the backbone model frozen and optimizes the policy with a faithfulness-oriented reward, avoiding direct edits to the model's stored knowledge. The abstract reports experiments on six datasets, with 0.01% additional trainable parameters, and says SPARK achieved more faithful generation than competitive baselines while preserving the backbone's general capabilities.

### Source excerpt

arXiv:2606.27786v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) enhances the faithfulness of large language models (LLMs) by incorporating external knowledge into the generation process. However, conflicts between retrieved context and parametric knowledge can cause LLMs to rely on inconsistent internal knowledge, hindering their ability to faithfully leverage retrieved evidence. Existing approaches mitigate this issue by editing parametric knowledge to resolve such conflicts. However, locating and modifying knowledge encoded in model parameters is challenging and may inadvertently compromise the backbone LLM's capabilities. In this paper, we introduce SPARK, a novel framework that formulates parametric knowledge control as a latent participation policy learning problem, enabling LLMs to adaptively regulate the contribution of parametric knowledge during generation. Specifically, SPARK introduces a lightweight participation policy that dynamically modulates the contribution of FFN-mediated parametric knowledge while keeping the backbone LLM frozen. The participation policy is optimized with a faithfulness-oriented reward, enabling fine-grained control over parametric knowledge participation during generation. Extensive experiments on six datasets validate the effectiveness of SPARK, which introduces and optimizes only 0.01\% additional trainable parameters while keeping the backbone LLM fully frozen, thereby preserving its general capabilities and achieving more faithful generation than competitive baselines. All datasets and code are available at https://github.com/OpenBMB/SPARK.

## Forget Freely, Grep Later: Lossless, Index-Free Memory for Long-Horizon LLM Agents

DevFeed: [Forget Freely, Grep Later: Lossless, Index-Free Memory for Long-Horizon LLM Agents](<https://devfeed.tech/articles/forget-freely-grep-later-lossless-index-free-memory-for-long-horizon-llm-agents-145470.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25123>)

Author: Ziyan Yang, Taiwei Shi, Jieyu Zhao

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>)

Tags: [agent-memory](<https://devfeed.tech/tags/agent-memory.md>), [agents](<https://devfeed.tech/tags/agents.md>), [context-management](<https://devfeed.tech/tags/context-management.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [expression](<https://devfeed.tech/tags/expression.md>), [grep](<https://devfeed.tech/tags/grep.md>), [index](<https://devfeed.tech/tags/index.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-agents](<https://devfeed.tech/tags/llm-agents.md>), [log](<https://devfeed.tech/tags/log.md>), [memory](<https://devfeed.tech/tags/memory.md>), [qwen3-5](<https://devfeed.tech/tags/qwen3-5.md>), [recall](<https://devfeed.tech/tags/recall.md>), [regular](<https://devfeed.tech/tags/regular.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [research](<https://devfeed.tech/tags/research.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [search](<https://devfeed.tech/tags/search.md>), [windows](<https://devfeed.tech/tags/windows.md>)

### AI overview

GrepMem stores an agent's complete history in an append-only plain-text log and uses regular-expression search for on-demand recall. This avoids the embeddings, retrieval index, memory extraction, and additional models used by structured memory approaches, while sidestepping losses from summarization or masking. In evaluations with Qwen3.5-9B trained by reinforcement learning, GrepMem reached 95-97% accuracy on ContextBench, compared with at most 21% for lossy baselines, and exceeded SUPO's summarization by 8.8 percentage points on BCP-Multi. The authors report effective scaling to longer streams and a position on the accuracy-token-cost Pareto frontier across five tasks. These results are limited to the reported evaluations; the supplied excerpt does not describe implementation details or broader deployment evidence.

### Source excerpt

arXiv:2611.25123v1 Announce Type: cross Abstract: Long-horizon LLM agents often exceed their context windows, forcing them to discard information that may be needed later. Existing context management strategies rely on summarization, masking, or structured memory, requiring decisions about what to preserve or how to retrieve it before future needs are known. However, these methods can introduce lossy compression, potentially discarding details needed for future tasks. To address this limitation, we introduce GrepMem, a simple, lossless, and index-free memory mechanism built on two components: an append-only plain-text log of the agent's complete history and a regular-expression search tool for on-demand recall. Unlike structured memory systems, GrepMem requires no embeddings, retrieval index, memory extraction, or additional models. We train Qwen3.5-9B with reinforcement learning under five context management strategies and evaluate on multi-question research sessions, long-stream recall, and agent-trajectory question answering. GrepMem achieves 95-97% accuracy on ContextBench, versus at most 21% for lossy baselines, and outperforms SUPO's summarization by 8.8 percentage points on BCP-Multi. GrepMem scales effectively to increasingly long input streams while remaining on the accuracy-token-cost Pareto frontier across all five evaluation tasks. Our results show that a plain-text log and grep provide a simple but competitive approach to long-horizon agent memory, without requiring complex structured memory infrastructure.

## Rate-distortion Assessment for Hierarchical Content Summarization

DevFeed: [Rate-distortion Assessment for Hierarchical Content Summarization](<https://devfeed.tech/articles/rate-distortion-assessment-for-hierarchical-content-summarization-145014.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25151>)

Author: Yunye Gong, Indranil Sur, Jared Claypoole, Pritish Sahu, Ajay Divakaran

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [ai evaluation](<https://devfeed.tech/topics/ai-evaluation.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>), [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>)

Tags: [assessment](<https://devfeed.tech/tags/assessment.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [budget](<https://devfeed.tech/tags/budget.md>), [compression](<https://devfeed.tech/tags/compression.md>), [content](<https://devfeed.tech/tags/content.md>), [context](<https://devfeed.tech/tags/context.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [design](<https://devfeed.tech/tags/design.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [encoding](<https://devfeed.tech/tags/encoding.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generation](<https://devfeed.tech/tags/generation.md>), [generative](<https://devfeed.tech/tags/generative.md>), [generative-models](<https://devfeed.tech/tags/generative-models.md>), [guidance](<https://devfeed.tech/tags/guidance.md>), [hierarchy](<https://devfeed.tech/tags/hierarchy.md>), [information](<https://devfeed.tech/tags/information.md>), [insights](<https://devfeed.tech/tags/insights.md>), [language](<https://devfeed.tech/tags/language.md>), [language-models](<https://devfeed.tech/tags/language-models.md>)

### AI overview

The paper frames hierarchical summarization as information encoding and proposes extracting a source's semantic hierarchy to measure the trade-off between compression rate and information distortion. This enables model comparisons at a chosen rate budget. The authors report experiments on long-context question-answering summaries using state-of-the-art large language models, aimed at assessing efficiency and comprehension, and say that using the hierarchy to guide retrieval-augmented generation improves rate-distortion characteristics over current baselines. The supplied text gives no quantitative results or details of the baselines.

### Source excerpt

arXiv:2611.25151v1 Announce Type: new Abstract: Powerful generative models including large language and vision models have demonstrated success across a wide range of content generation, editing and manipulation tasks via end-to-end prompt-based generation. However, current assessment of the quality of generative content manipulation remains subjective, limiting scientific understanding of model capabilities. Inspired by rate-distortion theory from Shannon information compression theory, in this work we formalize hierarchical content summarization as an information encoding problem. We design a principled framework to extract the semantic hierarchy of the source content to support quantitative characterization of the rate-distortion trade-off between compression efficiency (rate) against information loss (distortion) during generative content manipulation, which allows us to benchmark various models with respect to performance conditional on rate budget of interest. We demonstrate the use of the framework with empirical experiments on content summarization for long-context question-answering with state-of-the-art large language models, offering new insights into their efficiency and comprehension capabilities. We further demonstrate the use of the semantic hierarchy as guidance for performing effective retrieval augmented generation, showing improved rate-distortion characteristics against current baselines.

## Genie One Accuracy: Why Curated Agents Need Governed Context

DevFeed: [Genie One Accuracy: Why Curated Agents Need Governed Context](<https://devfeed.tech/articles/genie-one-accuracy-why-curated-agents-need-governed-context-144361.md>)

Original publisher: [Read original article](<https://www.databricks.com/blog/genie-one-accuracy-why-curated-agents-need-governed-context>)

Author: Richa Sethi; Patrick Chan

Published: 2026-11-19T20:15:41Z

Content type: news

Language: en

Sources: [Databricks](<https://devfeed.tech/sources/databricks.md>)

Topics: [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>), [enhancing AI model accuracy](<https://devfeed.tech/topics/enhancing-ai-model-accuracy.md>), [Data Quality](<https://devfeed.tech/topics/data-quality.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>)

Tags: [1-5](<https://devfeed.tech/tags/1-5.md>), [2025](<https://devfeed.tech/tags/2025.md>), [2027](<https://devfeed.tech/tags/2027.md>), [about](<https://devfeed.tech/tags/about.md>), [access-control](<https://devfeed.tech/tags/access-control.md>), [account](<https://devfeed.tech/tags/account.md>), [added](<https://devfeed.tech/tags/added.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-instructions](<https://devfeed.tech/tags/agent-instructions.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [all](<https://devfeed.tech/tags/all.md>), [also](<https://devfeed.tech/tags/also.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [context](<https://devfeed.tech/tags/context.md>), [data-strategy](<https://devfeed.tech/tags/data-strategy.md>), [finance](<https://devfeed.tech/tags/finance.md>), [genie](<https://devfeed.tech/tags/genie.md>), [governed-context](<https://devfeed.tech/tags/governed-context.md>), [need](<https://devfeed.tech/tags/need.md>), [one](<https://devfeed.tech/tags/one.md>), [ratio](<https://devfeed.tech/tags/ratio.md>)

### AI overview

In the fictional insurance benchmark, Genie One reached 93-95% accuracy when curated team agents were combined with governed Unity Catalog knowledge, compared with 64% using tables alone and 83% for either addition by itself. Agents helped answer questions requiring team documents; Metric Views and Pages supplied authoritative business definitions, reducing reliance on unrelated Pages and making definition answers accurate despite variable routing. Planted draft and prompt-injection documents did not change answers. A smaller retailer benchmark showed overall accuracy rising from 54% to 82% when governed knowledge was added to agents. The excerpt also shows limits: Genie One may answer directly without inheriting agent instructions, documents available only through agent search need agents, and formulas left in agents can become stale after a governed definition changes. The results come from fictional datasets and benchmarks, including a smaller retail check.

### Source excerpt

Ask Finance and Underwriting whether the loss ratio improved from 2024 to 2025, and...

## What Is a Vector Database? How It Works and Why AI Needs One

DevFeed: [What Is a Vector Database? How It Works and Why AI Needs One](<https://devfeed.tech/articles/what-is-a-vector-database-how-it-works-and-why-ai-needs-one-145883.md>)

Original publisher: [Read original article](<https://montecarlo.ai/blog-what-is-a-vector-database>)

Author: Virna Sekuj

Published: 2026-11-19T17:18:16Z

Content type: article

Language: en

Sources: [Monte Carlo](<https://devfeed.tech/sources/monte-carlo.md>)

Topics: [Vectors & LLMs](<https://devfeed.tech/topics/vectors-llms.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [vector embeddings in AI](<https://devfeed.tech/topics/vector-embeddings-in-ai.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [ann](<https://devfeed.tech/topics/ann.md>), [Database](<https://devfeed.tech/topics/database.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [hybrid-search](<https://devfeed.tech/topics/hybrid-search.md>)

Tags: [agent-trust](<https://devfeed.tech/tags/agent-trust.md>), [agent-trust-glossary](<https://devfeed.tech/tags/agent-trust-glossary.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [data](<https://devfeed.tech/tags/data.md>), [database](<https://devfeed.tech/tags/database.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [glossary](<https://devfeed.tech/tags/glossary.md>), [rag](<https://devfeed.tech/tags/rag.md>), [rag-systems](<https://devfeed.tech/tags/rag-systems.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [retrieval-augmented-generation](<https://devfeed.tech/tags/retrieval-augmented-generation.md>), [retrieval-augmented-generation-rag](<https://devfeed.tech/tags/retrieval-augmented-generation-rag.md>), [vector](<https://devfeed.tech/tags/vector.md>), [vector-database](<https://devfeed.tech/tags/vector-database.md>), [vector-database-examples](<https://devfeed.tech/tags/vector-database-examples.md>), [vector-database-for-rag](<https://devfeed.tech/tags/vector-database-for-rag.md>), [vector-database-vs-relational-database](<https://devfeed.tech/tags/vector-database-vs-relational-database.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-store](<https://devfeed.tech/tags/vector-store.md>)

### AI overview

Vector databases store content embeddings and use similarity search to retrieve relevant passages even when query wording differs. In a typical RAG flow, source content is chunked and embedded, stored with metadata, and indexed for approximate nearest-neighbor search; the user query is embedded and matching chunks are passed to the LLM as context. ANN indexing trades a small amount of precision for speed, and metadata filters can narrow results. Options include dedicated databases, database extensions, and vector search built into data platforms; choice depends on scale, latency, data location, and operational overhead. Retrieval can silently degrade when source syncs become stale, ingestion or chunking breaks, embedding models change without re-embedding, duplicate versions compete, or permission filters are missing. The text recommends monitoring freshness and ingestion volume, checking chunk quality, tracking embedding versions, measuring relevance and grounding, and tracing which chunks each agent request retrieves.

### Source excerpt

A vector database is a database built to store embeddings, which are numeric representations of the meaning of text, images, or other data, and to quickly find the embeddings most similar to a query. It's the retrieval layer behind most retrieval-augmented generation (RAG) systems and many AI agents, letting them find relevant information by meaning instead of exact keywords.

## What Is an LLM? Large Language Models Explained

DevFeed: [What Is an LLM? Large Language Models Explained](<https://devfeed.tech/articles/what-is-an-llm-large-language-models-explained-145885.md>)

Original publisher: [Read original article](<https://montecarlo.ai/blog-what-is-an-llm-large-language-models-explained>)

Author: Virna Sekuj

Published: 2026-11-19T16:43:33Z

Content type: article

Language: en

Sources: [Monte Carlo](<https://devfeed.tech/sources/monte-carlo.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [context window](<https://devfeed.tech/topics/context-window.md>), [knowledge cutoff](<https://devfeed.tech/topics/knowledge-cutoff.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [agent-trust](<https://devfeed.tech/tags/agent-trust.md>), [agent-trust-glossary](<https://devfeed.tech/tags/agent-trust-glossary.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [attention](<https://devfeed.tech/tags/attention.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [claude](<https://devfeed.tech/tags/claude.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [coding-assistants](<https://devfeed.tech/tags/coding-assistants.md>), [context](<https://devfeed.tech/tags/context.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [glossary](<https://devfeed.tech/tags/glossary.md>), [how-do-llms-work](<https://devfeed.tech/tags/how-do-llms-work.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-model](<https://devfeed.tech/tags/large-language-model.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-examples](<https://devfeed.tech/tags/llm-examples.md>), [llm-limitations](<https://devfeed.tech/tags/llm-limitations.md>), [llm-meaning](<https://devfeed.tech/tags/llm-meaning.md>), [llm-vs-ai-agent](<https://devfeed.tech/tags/llm-vs-ai-agent.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>)

### AI overview

LLMs generate text by predicting one token at a time, and their answers depend heavily on the context supplied at runtime. In production, fluent output can still be wrong because of hallucinations, stale or incomplete context, incorrect tool use, or provider model changes; failures may not show up in uptime or error rates. The excerpt recommends recording traces of prompts, retrieved data, tool calls, outputs, latency, token counts, and model versions; evaluating accuracy, relevance, and groundedness; checking context freshness and completeness; and tracking cost and performance. Comparing traces and data lineage can help distinguish a context problem from a model change. The excerpt does not cover full training stages in detail.

### Source excerpt

A large language model (LLM) is a neural network trained on large amounts of text to understand and generate human language. LLMs predict the most likely next piece of text, one token at a time, which lets them answer questions, write and summarize documents, generate code, and power AI agents that take actions.

## Microsoft adds knowledge graphs, retrieval model to Foundry IQ for better AI grounding

DevFeed: [Microsoft adds knowledge graphs, retrieval model to Foundry IQ for better AI grounding](<https://devfeed.tech/articles/microsoft-adds-knowledge-graphs-retrieval-model-to-foundry-iq-for-better-ai-grounding-143172.md>)

Original publisher: [Read original article](<https://www.infoworld.com/article/4250726/microsoft-adds-knowledge-graphs-retrieval-model-to-foundry-iq-for-better-ai-grounding.html>)

Author: Anirban Ghoshal

Published: 2026-11-19T12:56:43Z

Content type: news

Language: en

Sources: [InfoWorld](<https://devfeed.tech/sources/infoworld.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [AI-driven information retrieval](<https://devfeed.tech/topics/ai-driven-information-retrieval.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [Serverless](<https://devfeed.tech/topics/serverless.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-grounding](<https://devfeed.tech/tags/ai-grounding.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [analytics-artificial-intelligence-data-management](<https://devfeed.tech/tags/analytics-artificial-intelligence-data-management.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [automate](<https://devfeed.tech/tags/automate.md>), [build](<https://devfeed.tech/tags/build.md>), [build-ai-agents](<https://devfeed.tech/tags/build-ai-agents.md>), [business](<https://devfeed.tech/tags/business.md>), [capability](<https://devfeed.tech/tags/capability.md>), [conference](<https://devfeed.tech/tags/conference.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [connect](<https://devfeed.tech/tags/connect.md>), [data-management](<https://devfeed.tech/tags/data-management.md>), [foundry](<https://devfeed.tech/tags/foundry.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [grounding](<https://devfeed.tech/tags/grounding.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [model](<https://devfeed.tech/tags/model.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [storytype-news](<https://devfeed.tech/tags/storytype-news.md>)

### AI overview

Foundry IQ adds knowledge graphs, Microsoft-Retriever-1, and automatic retrieval-resource provisioning to help ground agents in enterprise data. Developers can supply an ontology or bring an existing graph; the service maps relationships across documents and records each connection's source, supporting questions that span multiple sources. Graphs are in public preview. Microsoft-Retriever-1 reformulates queries using enterprise terminology and decides whether to search again; it can be enabled on existing indexes and knowledge bases without extra provisioning or reindexing. It aims to reduce search rounds and reliance on large models for retrieval planning, though iterative searches may add latency and cost, and Microsoft has published no detailed performance comparisons. New Foundry projects will automatically receive a managed resource, removing the need to provision a separate Azure AI Search resource. That service is planned for public preview in December 2026, with usage-based serverless pricing. The text cautions that graph extraction can misread jargon or naming, graphs need validation and upkeep, and graph answers may cost more and take longer than routine search. Usage and

### Source excerpt

Microsoft is enhancing its Foundry IQ knowledge retrieval service with knowledge graphs, a specialized retrieval model and automatic infrastructure provisioning, seeking to make it easier for developers to build AI agents that can access, understand and reason over enterprise data. Grounding AI agents in organizational data is critical for enterprises to ensure they can deliver responses based on accurate, relevant, and up-to-date business information as they look to increasingly automate business workflows. The new knowledge graphs in Foundry IQ, announced at the Microsoft Ignite conference, will help agents connect related entities and facts across documents and organize enterprise content into topics, allowing them to answer questions that require information from multiple sources, the hyperscaler wrote in a blog post. In order to map relationships across documents, developers can add a graph configuration containing their ontology to an existing Foundry IQ knowledge source or bring an existing graph into the service. Foundry IQ then uses the ontology to map how documents, contacts, and information relate, while recording the source of each connection, it added. Alongside knowledge graphs, which are currently in public preview, the hyperscaler is adding a new retrieval model named Microsoft-Retriever-1 to reduce the number of searches and the reliance on large language models (LLMs) for retrieval planning in an effort to help developers lower latency and token consumption. The new model, according to the hyperscaler, interprets user queries, reformulates them using terminology found in enterprise documents, and determines whether additional searches are needed to retrieve relevant information. Developers can enable it on existing Foundry IQ indexes and knowledge bases without requiring additional provisioning or document reindexing, the hyperscaler wrote. Additionally, to simplify deployment of Foundry IQ, Microsoft is adding a capability that will automatically

## Evidence-Based Credit Assignment for Search-Augmented Language Models

DevFeed: [Evidence-Based Credit Assignment for Search-Augmented Language Models](<https://devfeed.tech/articles/evidence-based-credit-assignment-for-search-augmented-language-models-142705.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23824>)

Author: Wen Wang, Jindong Wang, Jiahua Bao, Tu Yongsiqi, Yihao Liu, Junwei He, Wenkui Fan

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [grpo](<https://devfeed.tech/topics/grpo.md>), [qwen](<https://devfeed.tech/topics/qwen.md>)

Tags: [credit-assignment](<https://devfeed.tech/tags/credit-assignment.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [evidence-based](<https://devfeed.tech/tags/evidence-based.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [search](<https://devfeed.tech/tags/search.md>)

### AI overview

Evidence-Based Credit Assignment (ECA) adds a training-only signal to terminal answer rewards for search-augmented language models. A frozen snapshot of the policy estimates how retrieved, deduplicated documents change the likelihood of a reference answer using a prompt containing only the question and evidence, helping distinguish useful searches even when sampled answers all fail. The paper compares ECA-Step, which accumulates step-clipped potential increments, with ECA-Horizon, which preserves the horizon-wide potential gain; both use cross-fold group normalization, novelty gating, and search-local token assignment. Across seven Search QA benchmarks, ECA-Horizon raises strict macro exact match over outcome-only GRPO by 1.03 points on Qwen2.5-3B-Instruct and 4.80 points on Qwen2.5-7B-Instruct, and reportedly outperforms RLOO and GiGPO. The abstract also reports zero-shot transfer to MultiHop-RAG; it provides no further evaluation details.

### Source excerpt

arXiv:2611.23824v1 Announce Type: new Abstract: Reinforcement learning from terminal answer rewards enables search-augmented language models to interleave reasoning and retrieval without step-level annotations, yet outcome supervision assigns identical credit to every search in a trajectory regardless of whether it retrieved useful information. This limitation is especially severe when all sampled rollouts for a question fail, collapsing group-centered outcome advantages to zero even when trajectories gather markedly different evidence. We present Evidence-based Credit Assignment (ECA), which augments terminal outcome rewards with a training-only auxiliary signal measuring how retrieved documents improve the likelihood of a reference answer. Rather than scoring the full dialogue prefix, ECA queries a frozen snapshot of the current policy under an evidence-only prompt containing solely the question and the deduplicated documents observed so far, isolating the utility of retrieved passages from surface variations in generated thoughts or search queries. Within this framework, we compare two return formulations, ECA-Step (which accumulates step-clipped potential increments) and ECA-Horizon (which preserves the telescoping horizon gain in potential), paired with cross-fold group normalization, novelty gating, and search-local token assignment. Across seven Search QA benchmarks, ECA-Horizon improves strict macro exact match over an outcome-only GRPO baseline by 1.03 and 4.80 percentage points on Qwen2.5-3B- and 7B-Instruct, respectively, outperforming both RLOO and GiGPO. Zero-shot evaluation on MultiHop-RAG further demonstrates strong transfer to multi-hop inference queries.

## Quantifying the Intrusiveness of Retrofitting Retrieval-Augmented Generation onto Legacy Software Systems

DevFeed: [Quantifying the Intrusiveness of Retrofitting Retrieval-Augmented Generation onto Legacy Software Systems](<https://devfeed.tech/articles/quantifying-the-intrusiveness-of-retrofitting-retrieval-augmented-generation-onto-legacy-software-systems-142202.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23931>)

Author: K. M. Tahlil Mahfuz Faruk, Rakib Abdullah

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Legacy Modernization](<https://devfeed.tech/topics/legacy-modernization.md>), [legacy systems](<https://devfeed.tech/topics/legacy-systems.md>), [AI Architecture](<https://devfeed.tech/topics/ai-architecture.md>), [software-architecture](<https://devfeed.tech/topics/software-architecture.md>), [performance-engineering](<https://devfeed.tech/topics/performance-engineering.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [backends](<https://devfeed.tech/tags/backends.md>), [call](<https://devfeed.tech/tags/call.md>), [case-study](<https://devfeed.tech/tags/case-study.md>), [churn](<https://devfeed.tech/tags/churn.md>), [code](<https://devfeed.tech/tags/code.md>), [commits](<https://devfeed.tech/tags/commits.md>), [coupling](<https://devfeed.tech/tags/coupling.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [delay](<https://devfeed.tech/tags/delay.md>), [dependency](<https://devfeed.tech/tags/dependency.md>), [enterprises](<https://devfeed.tech/tags/enterprises.md>), [generation](<https://devfeed.tech/tags/generation.md>), [legacy](<https://devfeed.tech/tags/legacy.md>), [legacy-software](<https://devfeed.tech/tags/legacy-software.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [retrieval-augmented-generation](<https://devfeed.tech/tags/retrieval-augmented-generation.md>), [software](<https://devfeed.tech/tags/software.md>), [software-systems](<https://devfeed.tech/tags/software-systems.md>), [systems](<https://devfeed.tech/tags/systems.md>)

### AI overview

The paper proposes three ways to add retrieval-augmented generation (RAG) to legacy software--sidecar, SDK-embed and naive-invasive--and a Legacy Intrusion Score (LIS) for comparing code changes, extended by LIS-X to cover operational effects. Across five systems, the code-level ranking is sidecar < SDK-embed < naive-invasive, though the authors say this follows from the metrics' component-wise dominance and validates the score rather than testing a hypothesis. In a live study on one host and one system, sidecar showed no detectable endpoint latency increase; SDK-embed and naive-invasive added 569 ms and 475 ms, with no significant difference. Both passed a 2-second dependency delay through to legacy requests, and RAG failure could leave successful responses without the AI field. RAG load slowed the legacy service on a shared host, while sidecar data staleness averaged 911 ms at a 2-second polling interval. These operational findings are limited to that single setup.

### Source excerpt

arXiv:2611.23931v1 Announce Type: new Abstract: Enterprises increasingly add retrieval-augmented generation (RAG) to existing REST and monolithic systems, usually by writing an ad hoc HTTP call into a handler, and have no way to quantify how intrusive that choice is. We present (1) a taxonomy of three retrofit patterns, sidecar, SDK-embed and naive-invasive; (2) the Legacy Intrusion Score (LIS), three code sub-metrics (churn, breadth, coupling), and an extension, LIS-X, with three operational sub-metrics measured on a live system (run-time overhead, fault propagation and silent feature degradation); (3) a static evaluation on five legacy systems, two of them real open-source codebases fetched from their repositories at pinned commits; and (4) a live case study that deploys all three patterns as separate OS processes. The code-level ranking sidecar < SDK-embed < naive-invasive holds in all five systems and under 2,000 random weightings, but it follows from component-wise dominance of the sub-metrics, so it validates the metric rather than testing a hypothesis. In the live study, outcomes are not fixed by definition. The sidecar adds no detectable latency to the legacy endpoint (0.07 ms, 95% CI [-0.10, 0.24]), whereas SDK-embed and naive-invasive add 569 and 475 ms and are not distinguishable from each other (p=0.62). Both pass a 2 s dependency delay on to legacy requests, and when the RAG layer fails fast they keep returning successful responses that no longer contain the AI field. Load on the RAG layer slows the legacy service by 1.51-1.57x on a shared host, and sidecar staleness averages 911 ms with a 2 s polling interval. Retrieval hit@1 is 0.95; three hosted LLMs answer all 12 test questions correctly and a local model 9/12, and the four backends are swapped by changing one request field. All dynamic results come from one host and one system.

## Making Mathematical Knowledge Explainable, Accessible and Interoperable Through Large Language Model Integration

DevFeed: [Making Mathematical Knowledge Explainable, Accessible and Interoperable Through Large Language Model Integration](<https://devfeed.tech/articles/making-mathematical-knowledge-explainable-accessible-and-interoperable-through-large-language-model-integration-142545.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2607.24512>)

Author: Jan Range, Bj\\"orn Schembera, Dominik G\\"oddeke

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [Vectors & LLMs](<https://devfeed.tech/topics/vectors-llms.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Wikidata](<https://devfeed.tech/topics/wikidata.md>)

Tags: [accessible](<https://devfeed.tech/tags/accessible.md>), [benefits](<https://devfeed.tech/tags/benefits.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-dl](<https://devfeed.tech/tags/cs-dl.md>), [explainability](<https://devfeed.tech/tags/explainability.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [interaction](<https://devfeed.tech/tags/interaction.md>), [interoperability](<https://devfeed.tech/tags/interoperability.md>), [join](<https://devfeed.tech/tags/join.md>), [knowledge-base](<https://devfeed.tech/tags/knowledge-base.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [large-language-model](<https://devfeed.tech/tags/large-language-model.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-protocol](<https://devfeed.tech/tags/mcp-protocol.md>), [mcp-server](<https://devfeed.tech/tags/mcp-server.md>), [metadata](<https://devfeed.tech/tags/metadata.md>), [model](<https://devfeed.tech/tags/model.md>), [model-context-protocol](<https://devfeed.tech/tags/model-context-protocol.md>), [model-context-protocol-mcp](<https://devfeed.tech/tags/model-context-protocol-mcp.md>), [models](<https://devfeed.tech/tags/models.md>), [natural-language](<https://devfeed.tech/tags/natural-language.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>)

### AI overview

MathModDB, a curated mathematical-model knowledge base built on Wikibase, can be difficult to use without navigating its complex interface or knowing SPARQL and Wikibase APIs; linking its records with research data in repositories such as Dataverse is also challenging. The paper proposes an MCP server that connects LLM dialogue to MathModDB using vector-indexed schema retrieval and a Steiner-tree-based join planner. The authors report that this approach improves accessibility and explainability while grounding LLM use in curated knowledge, and can simplify interoperability with external databases and tools. They present two use cases and say the architecture can extend to other Wikibase-based systems. The supplied text is an abstract, so it does not detail the use cases or evaluate performance.

### Source excerpt

arXiv:2607.24512v2 Announce Type: replace Abstract: Mathematical models are central to formalizing research problems, yet their documentation often falls short of FAIR principles. Knowledge bases such as the Mathematical Model Database (MathModDB) address this gap by providing curated, semantically rich representations of mathematical models. Built on Wikibase, the same open-source infrastructure underlying Wikidata, MathModDB utilizes Semantic Web technologies to support Linked Open Data, collaborative editing, and the storage of semantically enriched metadata, making it a domain-specific knowledge graph within the broader Wikidata ecosystem. However, access to MathModDB currently requires either navigating a complex web interface or proficiency in SPARQL and Wikibase APIs, posing significant barriers for potential users. In addition, the combination of such curated knowledge bases with actual research data stored, e.g., in Dataverse repository instances, remains a challenge. To overcome these limitations, we propose integrating Large Language Models (LLMs) with MathModDB via a Model Context Protocol (MCP) server that exposes a vector-indexed schema retrieval and Steiner-tree-based join planner, combining dialogue-based natural language interaction with curated, epistemically grounded knowledge. Although instantiated on MathModDB, the architecture can be applied to other Wikibase-based systems. We demonstrate that this approach enables epistemically grounded LLM usage, improves model explainability and accessibility beyond what the standard Wikibase interface offers, and simplifies interoperability with external databases and tools, such as Dataverse data repositories. We illustrate the benefits of combining the accessibility of an LLM with the epistemic safety of a curated knowledge base through the adaptability of the MCP protocol by two use cases.

## FutureBench: A Renewable Framework for Evaluating Knowledge-Context Conflict in LLMs

DevFeed: [FutureBench: A Renewable Framework for Evaluating Knowledge-Context Conflict in LLMs](<https://devfeed.tech/articles/futurebench-a-renewable-framework-for-evaluating-knowledge-context-conflict-in-llms-142677.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23601>)

Author: Yi-Cheng Lai, Hen-Hsen Huang

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [knowledge cutoff](<https://devfeed.tech/topics/knowledge-cutoff.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>)

Tags: [adoption](<https://devfeed.tech/tags/adoption.md>), [adversarial](<https://devfeed.tech/tags/adversarial.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [events](<https://devfeed.tech/tags/events.md>), [framework](<https://devfeed.tech/tags/framework.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [llms](<https://devfeed.tech/tags/llms.md>), [models](<https://devfeed.tech/tags/models.md>), [priority](<https://devfeed.tech/tags/priority.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [questions](<https://devfeed.tech/tags/questions.md>), [source](<https://devfeed.tech/tags/source.md>)

### AI overview

FutureBench evaluates how LLMs handle conflicts between retrieved passages and model knowledge using timestamped questions, controlled passage triplets, and no-context probes. Across 3,629 questions and six models, Verify--a prompt combining checking with passage priority--raised adoption of false answers for pre-cutoff events in all five models tested, mainly by displacing answers that Baseline had answered correctly while allowing both passage evidence and model knowledge. For post-cutoff events, only o4-mini increased adoption (+13.7 percentage points). In a separate comparison of 902 post-cutoff questions, passage priority without checking raised adoption, while switching to Verify lowered it in all five models. Adversarial-Aware, which warns about misleading passages and prioritizes model knowledge, restored 82.5-98.9% of displaced pre-cutoff answers, with under one percentage point change in accuracy when passages were true. The framework supports repeat evaluation on fixed cohorts and extension to new events as models change.

### Source excerpt

arXiv:2611.23601v1 Announce Type: cross Abstract: Asking a model to check retrieved text can also tell it which source to trust. We introduce FutureBench, a renewable framework for evaluating knowledge-context conflict using timestamped questions, controlled passage triplets, and no-context probes. Across 3,629 questions and six models, Verify (a prompt combining checking with passage priority) raises false-answer adoption in all five models tested on pre-cutoff events, mainly by displacing answers that were correct under Baseline, which allows both passage evidence and model knowledge. On post-cutoff events, only o4-mini increases adoption (+13.7 percentage points). A four-prompt comparison on 902 post-cutoff questions finds that passage priority without checking raises adoption, while moving to Verify lowers it in all five models. Adversarial-Aware, which warns of misleading passages and prioritizes model knowledge, restores 82.5-98.9% of displaced pre-cutoff answers with under one point of change in true-passage accuracy. FutureBench supports repeated evaluation on fixed cohorts and extension to new events as models change.

## KnowledgeClaw: Towards Agentic Knowledge Engineering via Omnimodal Hypergraphs

DevFeed: [KnowledgeClaw: Towards Agentic Knowledge Engineering via Omnimodal Hypergraphs](<https://devfeed.tech/articles/knowledgeclaw-towards-agentic-knowledge-engineering-via-omnimodal-hypergraphs-142774.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24294>)

Author: Haoran Luo, Jiapu Wang, Linhao Luo, Luu Anh Tuan

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [application](<https://devfeed.tech/tags/application.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [bench](<https://devfeed.tech/tags/bench.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [data](<https://devfeed.tech/tags/data.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [files](<https://devfeed.tech/tags/files.md>), [graph](<https://devfeed.tech/tags/graph.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-engineering](<https://devfeed.tech/tags/knowledge-engineering.md>), [lifecycle](<https://devfeed.tech/tags/lifecycle.md>), [live](<https://devfeed.tech/tags/live.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-agents](<https://devfeed.tech/tags/llm-agents.md>), [memory](<https://devfeed.tech/tags/memory.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [query](<https://devfeed.tech/tags/query.md>), [rag](<https://devfeed.tech/tags/rag.md>)

### AI overview

KnowledgeClaw combines an omnimodal typed hypergraph, a closed-loop agent that keeps the knowledge base current, and query routing to the needed granularity. The paper introduces OmniKE as the combination of omnimodality, lifecycle management, and multi-granular use, and reports that existing systems address at most two of these together. Its OmniKE-Bench contains six tasks and 1,829 model-free items drawn from 3,960 real files across five modalities. Against 30 baselines, KnowledgeClaw ranks first on all six tasks, with an overall OKE score of 55.9--14.6 above the strongest baseline. These are results reported in the supplied abstract excerpt.

### Source excerpt

arXiv:2611.24294v1 Announce Type: new Abstract: Knowledge engineering (KE) turns raw files into a reasoning-ready knowledge base, a task now within reach of LLM agents. KE has progressed from chunk and graph retrieval-augmented generation (RAG) to memory agents, agentic KE and multimodal KE. However, a live knowledge base needs omnimodality, a closed-loop lifecycle and multi-granular application at once, yet existing systems meet at most two and no benchmark measures all three. We formalize Omnimodal Knowledge Engineering (OmniKE) and release OmniKE-Bench, six tasks with 1,829 model-free items over 3,960 real files in five modalities. We further propose KnowledgeClaw, an agentic system that builds an omnimodal typed hypergraph, keeps it current with a closed-loop lifecycle agent and routes each query to the granularity it needs. Against 30 baselines, it ranks first on all six tasks with an overall OKE of 55.9, +14.6 over the strongest baseline. Our software and data are publicly available at https://github.com/LHRLAB/KnowledgeClaw.

## Disagreement-Guided Agentic Data Curation for Multimodal Safety

DevFeed: [Disagreement-Guided Agentic Data Curation for Multimodal Safety](<https://devfeed.tech/articles/disagreement-guided-agentic-data-curation-for-multimodal-safety-142542.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2607.14256>)

Author: Genglin Liu, Muye Zhang, Krishnamurthy Viswanathan, Nichole J. Hansen, Bla\\v{z} Bratani\\v{c}, Nathan L Clement, Shalini Ghosh, Ariel Fuxman

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [ai safety](<https://devfeed.tech/topics/ai-safety.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [responsible-ai](<https://devfeed.tech/topics/responsible-ai.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ma](<https://devfeed.tech/tags/cs-ma.md>), [curation](<https://devfeed.tech/tags/curation.md>), [data](<https://devfeed.tech/tags/data.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [grounding](<https://devfeed.tech/tags/grounding.md>), [images](<https://devfeed.tech/tags/images.md>), [memory](<https://devfeed.tech/tags/memory.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [policies](<https://devfeed.tech/tags/policies.md>), [policy](<https://devfeed.tech/tags/policy.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [safety](<https://devfeed.tech/tags/safety.md>), [selection](<https://devfeed.tech/tags/selection.md>), [signal](<https://devfeed.tech/tags/signal.md>)

### AI overview

The pipeline uses disagreement to curate synthetic boundary cases for multimodal safety evaluation: it generates policy-conditioned images, selects cases where a target model and rater or multiple raters disagree, conditionally escalates unresolved cases, then retrieves labeled examples as in-context demonstrations. On a failure-enriched benchmark, policy grounding lowers false negative rate (FNR) from 0.875 to 0.413 and raises F1 from 0.220 to 0.731. Retrieving 50 disagreement-selected examples lowers FNR further to 0.245, versus 0.297 with a 350-example Regular pool. The selected memory also improves a different target-model family, with a smaller gain on a proprietary benchmark using a refined policy. In a blinded human study, experts disagreed on 24% of disagreement-guided images and 17% of baseline-curated images. The results support this approach for safety evaluation and example selection; the excerpt does not establish how it performs beyond the reported benchmarks.

### Source excerpt

arXiv:2607.14256v2 Announce Type: replace Abstract: Written safety policies in multimodal settings define categories whose visual boundaries span many contexts. We study disagreement as a signal for identifying useful synthetic boundary cases. Our pipeline generates policy-conditioned images, selects cases with target--rater or inter-rater disagreement, conditionally escalates unresolved cases, and retrieves the resulting rater-labeled examples as in-context demonstrations. On a failure-enriched multimodal safety benchmark, policy grounding reduces false negative rate (FNR) from 0.875 to 0.413 and raises F1 from 0.220 to 0.731; retrieval from 50 disagreement-selected examples further reduces FNR to 0.245, compared with 0.297 from a 350-example Regular pool. The selected memory also improves a different target-model family, with a smaller gain on a proprietary benchmark with a refined policy. In a blinded human study, experts disagree on 24% of disagreement-guided images and 17% of baseline-curated images. These findings support traceable, disagreement-guided curation for multimodal safety evaluation and example selection.

## NaviGATE: Noise-Aware Dual-View Generation for Multimodal Knowledge Graph Reasoning

DevFeed: [NaviGATE: Noise-Aware Dual-View Generation for Multimodal Knowledge Graph Reasoning](<https://devfeed.tech/articles/navigate-noise-aware-dual-view-generation-for-multimodal-knowledge-graph-reasoning-142808.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24552>)

Author: Jie Peng, Yongxue Shan, Yongfu Zha, Cui Miao, Xiaodong Wang

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>)

Tags: [activation](<https://devfeed.tech/tags/activation.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [generation](<https://devfeed.tech/tags/generation.md>), [generative](<https://devfeed.tech/tags/generative.md>), [graph](<https://devfeed.tech/tags/graph.md>), [inference](<https://devfeed.tech/tags/inference.md>), [instruction-tuning](<https://devfeed.tech/tags/instruction-tuning.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [noise](<https://devfeed.tech/tags/noise.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [robust](<https://devfeed.tech/tags/robust.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [semantics](<https://devfeed.tech/tags/semantics.md>), [stage](<https://devfeed.tech/tags/stage.md>), [view](<https://devfeed.tech/tags/view.md>)

### AI overview

NaviGATE addresses noisy retrieval and invalid entity generation in multimodal knowledge graph reasoning. It aligns graph structure with text, fine-tunes a multimodal language model using entity summaries and structural tokens, then trains retrieval-free and retrieval-aware views together. Contrastive logit sharpening reinforces reliable retrieved candidates; parametric consistency distillation suppresses misleading ones. At inference, structure-constrained decoding limits outputs to valid graph entities. The abstract reports that NaviGATE outperforms strong unimodal, multimodal, and generation-based baselines on standard benchmarks and remains robust under noisy retrieval.

### Source excerpt

arXiv:2611.24552v1 Announce Type: new Abstract: Multimodal knowledge graph reasoning (MKGR) aims to infer missing facts by jointly exploiting relational structures, textual descriptions, and visual evidence. Existing embedding-based methods effectively capture graph topology, but their fixed multimodal representations are less effective for query-specific fine-grained semantic reasoning, while generation-based methods are vulnerable to noisy retrieval and may produce invalid entities. To address these challenges, we propose NaviGATE, a noise-aware generative framework for MKGR. NaviGATE first aligns graph-derived structural representations with textual semantics, then performs structure-aware internal knowledge activation by fine-tuning the multimodal language model with multimodal entity summaries and injected structural tokens. In the noise-aware dual-view instruction tuning stage, NaviGATE jointly optimizes retrieval-free and retrieval-aware views: reliable retrieved candidates are reinforced through contrastive logit sharpening, while misleading candidates are suppressed through parametric consistency distillation. In inference, structure-constrained decoding restricts generation to valid entities in the target knowledge graph. Experiments on standard benchmarks show that NaviGATE consistently outperforms strong unimodal, multimodal, and generation-based baselines, and remains robust under noisy retrieval scenarios.

## MemeLogos: Knowledge-Driven Retrieval-Augmented Reasoning for Harmful Meme Detection

DevFeed: [MemeLogos: Knowledge-Driven Retrieval-Augmented Reasoning for Harmful Meme Detection](<https://devfeed.tech/articles/memelogos-knowledge-driven-retrieval-augmented-reasoning-for-harmful-meme-detection-142575.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.15463>)

Author: Hexiang Gu, Saihui Hou, Changlan Liu, Min Ren, Huijia Wu, Hongxun Gu, Zhaofeng He

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>)

Tags: [coherent](<https://devfeed.tech/tags/coherent.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [detection](<https://devfeed.tech/tags/detection.md>), [graph](<https://devfeed.tech/tags/graph.md>), [interpretability](<https://devfeed.tech/tags/interpretability.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [memes](<https://devfeed.tech/tags/memes.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [patterns](<https://devfeed.tech/tags/patterns.md>), [performance](<https://devfeed.tech/tags/performance.md>), [process](<https://devfeed.tech/tags/process.md>), [rag](<https://devfeed.tech/tags/rag.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [retrieval-augmented-generation](<https://devfeed.tech/tags/retrieval-augmented-generation.md>), [social-media](<https://devfeed.tech/tags/social-media.md>), [units](<https://devfeed.tech/tags/units.md>)

### AI overview

MemeLogos detects harmful memes by turning recurring harmfulness patterns and reasoning structures into reusable knowledge units, organizing them in a star-shaped graph, and retrieving that structured knowledge to guide an explicit, multi-stage reasoning process. The authors report that it consistently outperforms existing detection methods and produces more coherent, interpretable reasoning. The supplied abstract does not provide experimental details or quantitative results.

### Source excerpt

arXiv:2610.15463v3 Announce Type: replace Abstract: With the rapid proliferation of social media, harmful memes have become a growing threat to online ecosystems. Their harmfulness is often implicitly conveyed through complex interactions among visual, textual, and contextual cues, making accurate detection challenging. Recent studies have introduced Retrieval-Augmented Generation (RAG) and external knowledge into harmful meme detection. However, existing methods mainly retrieve similar instances or auxiliary information, limiting their ability to capture reusable harmfulness knowledge and underlying reasoning mechanisms, and thus constraining both detection performance and interpretability. To address these challenges, we propose MemeLogos, a knowledge-driven retrieval-augmented reasoning framework for harmful meme detection. MemeLogos abstracts recurring harmfulness patterns and reasoning structures from diverse harmful cases into reusable knowledge units and organizes them into a dedicated star-shaped knowledge graph. By combining structured knowledge retrieval with an explicit multi-stage reasoning process inspired by cognitive mechanisms, MemeLogos leverages retrieved knowledge to guide harmfulness reasoning, improving both detection reliability and interpretability. Extensive experiments show that MemeLogos consistently outperforms existing harmful meme detection methods while generating more coherent and interpretable reasoning, demonstrating the effectiveness of structured harmfulness knowledge for multimodal content understanding.

## Tether solves the memory challenge for AI builders who don't want to rely on the cloud

DevFeed: [Tether solves the memory challenge for AI builders who don't want to rely on the cloud](<https://devfeed.tech/articles/tether-solves-the-memory-challenge-for-ai-builders-who-don-t-want-to-rely-on-the-cloud-141204.md>)

Original publisher: [Read original article](<https://www.cio.com/article/4250405/tether-solves-the-memory-challenge-for-ai-builders-who-dont-want-to-rely-on-the-cloud.html>)

Author: tether

Published: 2026-11-18T20:54:28Z

Content type: article

Language: en

Sources: [CIO](<https://devfeed.tech/sources/cio.md>)

Topics: [Local AI](<https://devfeed.tech/topics/local-ai.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [quantization](<https://devfeed.tech/topics/quantization.md>), [context window](<https://devfeed.tech/topics/context-window.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-machine-learning](<https://devfeed.tech/tags/artificial-intelligence-machine-learning.md>), [cache](<https://devfeed.tech/tags/cache.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [compression](<https://devfeed.tech/tags/compression.md>), [context](<https://devfeed.tech/tags/context.md>), [database](<https://devfeed.tech/tags/database.md>), [development-kit](<https://devfeed.tech/tags/development-kit.md>), [device](<https://devfeed.tech/tags/device.md>), [edition-us](<https://devfeed.tech/tags/edition-us.md>), [inference](<https://devfeed.tech/tags/inference.md>), [kv-cache](<https://devfeed.tech/tags/kv-cache.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [local-ai](<https://devfeed.tech/tags/local-ai.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [memory](<https://devfeed.tech/tags/memory.md>), [model](<https://devfeed.tech/tags/model.md>), [model-weights](<https://devfeed.tech/tags/model-weights.md>), [on-device](<https://devfeed.tech/tags/on-device.md>), [on-device-ai](<https://devfeed.tech/tags/on-device-ai.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [phone](<https://devfeed.tech/tags/phone.md>), [qwen3-5](<https://devfeed.tech/tags/qwen3-5.md>), [qwen3-5-4b](<https://devfeed.tech/tags/qwen3-5-4b.md>), [storytype-brandpost](<https://devfeed.tech/tags/storytype-brandpost.md>)

### AI overview

Tether's QVAC SDK uses two quantization tools to reduce memory demands in local AI: TurboQuant compresses a model's KV cache during inference, while TurboVec compresses the vector index used for retrieval-augmented generation (RAG). The excerpt reports TurboQuant can cut context memory by up to five times; for Qwen3.5-4B at 262,000 tokens, it gives a comparison of about 8 GB for a standard 16-bit cache versus 1.6 GB with TurboQuant. TurboVec reportedly reduces ten million typical embedding vectors from roughly 61 GB to about 8 GB. TurboQuant was integrated in QVAC SDK v0.12.0 for Windows and Linux systems with NVIDIA, AMD, or Intel GPUs. The article presents these savings as enabling longer contexts and document search on consumer hardware, potentially supporting private-data RAG without cloud uploads. The provided text ends partway through the KV-cache example, so it does not show the full discussion.

### Source excerpt

Thanks to the rise of a new generation of highly capable small AI models, on-device or local inference has become increasingly viable for a greater range of applications. However, limited memory capacity often prevents local AI from reaching its full potential. A model that fits comfortably on a laptop or phone can hit a wall the moment it has to hold a long conversation or search a large database. To advance on-device AI capabilities, Tether's QVAC SDK tackles the memory challenge from two directions. By integrating TurboQuant and TurboVec, the software development kit shrinks two of the biggest memory costs in a local AI pipeline: the model's working memory during inference, and the index it searches when answering questions from your own documents. Compressing what AI remembers Modern language models generate text through a process called self-attention, in which each token (the basic units of text) gets encoded into three vectors: a query, a key, and a value. The query is what the current token is "looking for"; the key is what each earlier token offers up to be matched against that query; and the value is the actual content pulled forward once a match is found. AI models don't reprocess the whole conversation for every new word. They keep a running store of key and value projections for every token already seen: the KV cache. Originally developed by Google researchers, TurboQuant is an open-source compression algorithm for this KV cache that transforms 16- or 32-bit vectors into smaller ones, without losing too much accuracy. The result is up to a five times reduction in the amount of memory used to store context during inference. Reducing the size of a model's KV cache enables AI running on consumer hardware to process longer context prompts that would otherwise exceed local memory capacity. Consider a four billion parameter model like Qwen3.5-4B running at 262,000 tokens of context. While the model weights alone are small enough to fit on a smartphone's VRAM,

[Next page](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md?cursor=WyIyMDI2LTExLTE4VDIwOjU0OjI4KzAwOjAwIiwgIjYyZGUxZWNhLTFiY2MtNDE1Ny1iNWI2LWM1YTUwM2NlMDI3ZiJd>)