# information retrieval

Information retrieval is a computing field concerned with organizing, accessing, and ranking information so users can locate relevant items.

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

## 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.

## From Sessions to Serving: Integrating LLM-Based Embeddings into Retrieval for Production Content Recommendation

DevFeed: [From Sessions to Serving: Integrating LLM-Based Embeddings into Retrieval for Production Content Recommendation](<https://devfeed.tech/articles/from-sessions-to-serving-integrating-llm-based-embeddings-into-retrieval-for-production-content-recommendation-145141.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26096>)

Author: Zhixiong Hu, Meng Li, Maggie Zhang, Deborshi Goswami, David Bailey, James Bradley

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

Content type: article

Language: en

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

Topics: [recommendation systems](<https://devfeed.tech/topics/recommendation-systems.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [personalization](<https://devfeed.tech/topics/personalization.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>)

Tags: [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [llm](<https://devfeed.tech/tags/llm.md>), [production](<https://devfeed.tech/tags/production.md>), [recommendation](<https://devfeed.tech/tags/recommendation.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [serving](<https://devfeed.tech/tags/serving.md>)

### AI overview

LSER adds session- and history-level embeddings from a pretrained LLM as auxiliary user-side signals in the retrieval-stage user tower, alongside existing learned sequence encoders. For freshness as behavior changes, an asynchronous nearline serving path refreshes sequential and LLM-derived user vectors for the recommendation server. An ablation across a multi-content-type catalog indicates the LLM features can improve model performance, and the authors report that this approach is technically feasible in production. The excerpt gives no quantitative results or details of the serving implementation.

### Source excerpt

arXiv:2611.26096v1 Announce Type: cross Abstract: Personalized content recommendation on large marketplace websites must reconcile heterogeneous candidate content (e.g., customer stories, product pages, industry pages, and learning content) with sparse, fast-changing user behavior, placing increasing demands on the retrieval stage to represent user interest well, not just the downstream ranking stage. We present LSER (LLM Session Embedding Retrieval), a production content recommendation system for autodesk.com that derives session- and history-level embeddings from a pretrained large language model (LLM) and adds them as auxiliary user-side features in the retrieval-stage user tower alongside existing learned sequence encoders. To keep user-side embeddings fresh under real-time behavior, we build a nearline serving path that asynchronously refreshes sequential and LLM-derived user vectors for our main content recommendation server. We validate the incremental value of the LLM features through an ablation study across our full multi-content-type catalog. Our results indicate that integrating LLM-derived embeddings as additional retrieval signals, together with production-grade nearline serving, is technically feasible and can improve model performances.

## Learning Generative Ranking Policies for Whole-Page Optimization

DevFeed: [Learning Generative Ranking Policies for Whole-Page Optimization](<https://devfeed.tech/articles/learning-generative-ranking-policies-for-whole-page-optimization-145066.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25527>)

Author: Chen Qiu, Zhigang Hua, Qi Xu, Jizhe Zhang, Sha Hua, Ren Mao, Luke Simon

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

Content type: article

Language: en

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

Topics: [recommendation systems](<https://devfeed.tech/topics/recommendation-systems.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Combinatorial optimization](<https://devfeed.tech/topics/combinatorial-optimization.md>)

Tags: [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [generative](<https://devfeed.tech/tags/generative.md>), [improvement](<https://devfeed.tech/tags/improvement.md>), [learning](<https://devfeed.tech/tags/learning.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [pages](<https://devfeed.tech/tags/pages.md>), [policies](<https://devfeed.tech/tags/policies.md>), [ranking](<https://devfeed.tech/tags/ranking.md>), [recommendation](<https://devfeed.tech/tags/recommendation.md>)

### AI overview

The paper proposes whole-page policy improvement for recommendation ranking, choosing and ordering items jointly because items can compete for attention or complement one another. Its local page-level objective repeatedly moves the generator toward higher-scoring pages and splits into a target for each position: at the same partial page, candidates are compared by the scores of the complete pages they lead to. This aims to train each choice for its contribution to the whole page. The authors report better results than evaluated generative re-ranking baselines on KuaiRand-1K, RL4RS-SeqSlate, and an industrial logged-page dataset, and performance closest to the known optimum on a synthetic benchmark. The supplied text does not provide metric values or experimental details.

### Source excerpt

arXiv:2611.25527v1 Announce Type: cross Abstract: A recommendation page is consumed as a whole: the items on it compete for attention and complement one another, so the best page is not simply the individually best items placed side by side. We study whole-page optimization, which selects and orders the items on a page jointly to maximize the score of the page. The number of possible pages grows combinatorially, so good pages must be generated rather than enumerated. Some generative re-ranking methods use the same page-level training signal for every choice in a sampled page. Others imitate target pages built before training, which remain largely fixed as the generator improves. We address both limitations with one local page-level objective, which repeatedly moves the current generator toward pages with higher score. This objective splits exactly into one training target per position, and each target compares candidates at the same partial page by the scores of the complete pages they lead to. Every position therefore learns to choose the item that is better for the whole page, rather than the item that looks best on its own. We call this procedure whole-page policy improvement. On two public datasets, KuaiRand-1K and RL4RS-SeqSlate, which cover multi-objective item selection and constrained ordering, and on an industrial dataset of logged pages, our method outperforms the evaluated generative re-ranking baselines. On a synthetic benchmark with a known optimal page, it also comes closest to the optimum, showing that its improvements come from better whole-page decisions.

## 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.

## 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

## PMKPIR: Parallel Multi-Keyword PIR with Interleaved Batching for Private Boolean Retrieval

DevFeed: [PMKPIR: Parallel Multi-Keyword PIR with Interleaved Batching for Private Boolean Retrieval](<https://devfeed.tech/articles/pmkpir-parallel-multi-keyword-pir-with-interleaved-batching-for-private-boolean-retrieval-143148.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24248>)

Author: Rongxi Wang, Guanxiong Ha, Chunfu Jia, Minfen Gao, Hanmiaomiao Wang

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

Content type: article

Language: en

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

Topics: [Cryptography](<https://devfeed.tech/topics/cryptography.md>), [homomorphic encryption](<https://devfeed.tech/topics/homomorphic-encryption.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [vectorization techniques](<https://devfeed.tech/topics/vectorization-techniques.md>)

Tags: [batching](<https://devfeed.tech/tags/batching.md>), [boolean](<https://devfeed.tech/tags/boolean.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [homomorphic-encryption](<https://devfeed.tech/tags/homomorphic-encryption.md>), [matching](<https://devfeed.tech/tags/matching.md>), [parallel](<https://devfeed.tech/tags/parallel.md>), [pir](<https://devfeed.tech/tags/pir.md>), [private](<https://devfeed.tech/tags/private.md>), [query-processing](<https://devfeed.tech/tags/query-processing.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [security](<https://devfeed.tech/tags/security.md>), [security-analysis](<https://devfeed.tech/tags/security-analysis.md>), [simd](<https://devfeed.tech/tags/simd.md>), [storage](<https://devfeed.tech/tags/storage.md>), [time](<https://devfeed.tech/tags/time.md>), [traversal](<https://devfeed.tech/tags/traversal.md>)

### AI overview

PMKPIR combines interleaved batching with BFV homomorphic encryption to support parallel multi-keyword matching and universal Boolean computation while preserving the core security guarantees of classic PIR, according to the authors' analysis. Its IBPIR component matches multiple keywords in one database traversal; a Boolean query method extends that parallelism to Boolean operations. Against state-of-the-art schemes, the authors report reductions of up to 79.06% in query time, 75.00% in communication overhead, 97.92% in storage overhead, and 80.26% in peak memory. These are maximum reported reductions; the excerpt gives no benchmark conditions or per-scheme results.

### Source excerpt

arXiv:2611.24248v1 Announce Type: new Abstract: Keyword Private Information Retrieval (Keyword PIR) allows users to retrieve data associated with specific keywords from a database while protecting query privacy. However, existing Keyword PIR schemes supporting boolean retrieval either incur high computational overhead due to multiple database traversals, or fail to support universal boolean computation. We propose PMKPIR, a novel keyword PIR scheme supporting both parallel multi-keyword queries and universal boolean computation. We utilize the single instruction multiple data (SIMD) capability of BFV homomorphic encryption to propose an interleaved batching method, and design IBPIR based on this method, achieving the private matching of multiple keywords in a single database traversal. Furthermore, we design a boolean query processing method, extending the parallel capability of interleaved batching from keyword querying to boolean query computation, to support universal boolean computation and accelerate boolean operations. Building upon IBPIR, we integrate this method to further design PMKPIR. To the best of our knowledge, PMKPIR is the first Keyword PIR scheme to support multi-keyword batch matching within boolean queries. Security analysis demonstrates that, consistent with existing PIR schemes supporting boolean retrieval, PMKPIR preserves the core security guarantees of classic PIR. Compared with state-of-the-art schemes, PMKPIR reduces query time, communication overhead, storage overhead, and peak memory by up to 79.06%, 75.00%, 97.92%, and 80.26%, respectively.

## SurgCBVR: A Multi-Domain Benchmark for Content-Based Surgical Video-to-Video Retrieval

DevFeed: [SurgCBVR: A Multi-Domain Benchmark for Content-Based Surgical Video-to-Video Retrieval](<https://devfeed.tech/articles/surgcbvr-a-multi-domain-benchmark-for-content-based-surgical-video-to-video-retrieval-142641.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23347>)

Author: Mohammad Eslami, Mousa Moradi, Negin Ghamsarian, Nazlee Zebardast, Jennifer L Lindsey, Sophia Y. Wang, Lucia Sobrin, Rishi P Singh, Tobias Elze

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-driven information retrieval](<https://devfeed.tech/topics/ai-driven-information-retrieval.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [Video Analytics](<https://devfeed.tech/topics/video-analytics.md>), [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [based](<https://devfeed.tech/tags/based.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cases](<https://devfeed.tech/tags/cases.md>), [classes](<https://devfeed.tech/tags/classes.md>), [classifier](<https://devfeed.tech/tags/classifier.md>), [clip](<https://devfeed.tech/tags/clip.md>), [computer](<https://devfeed.tech/tags/computer.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [content](<https://devfeed.tech/tags/content.md>), [counts](<https://devfeed.tech/tags/counts.md>), [covering](<https://devfeed.tech/tags/covering.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [domain](<https://devfeed.tech/tags/domain.md>), [domains](<https://devfeed.tech/tags/domains.md>), [eess-iv](<https://devfeed.tech/tags/eess-iv.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [video](<https://devfeed.tech/tags/video.md>)

### AI overview

SurgCBVR benchmarks surgical video-to-video retrieval across eight public datasets: 679 cases and 76,489 clips from six procedure types in ophthalmic, laparoscopic, robotic-assisted, and colonoscopy domains. Its Scene tier retrieves matching operative states across cases and sites; Workflow retrieves and localizes phase transitions and deviations. Fixed clip lengths and frame counts, plus phase-classifier oracle and duration-only baselines, are used to check for label and timing shortcuts. Evaluation covers six generic and surgical foundation models, two retrieval methods, and contrastive heads, with within-dataset, cross-dataset, and pooled-gallery settings restricted to the same procedure type. Frozen representations barely beat a timing-only baseline, transition retrieval is near chance, and trained heads lose up to half their accuracy across datasets, indicating weak generalization in current representations.

### Source excerpt

arXiv:2611.23347v1 Announce Type: cross Abstract: Hospitals record thousands of hours of surgical video annually, yet these archives remain difficult to search by content. Surgeons cannot readily retrieve similar operations, complications, or workflow events. Existing surgical computer vision primarily produces labels rather than retrieving relevant videos. We introduce SurgCBVR, the first benchmark for content-based video-to-video retrieval in surgery. It integrates eight public datasets across four domains-ophthalmic, laparoscopic, robotic-assisted, and colonoscopy-covering six procedure types, 679 cases, and 76,489 clips (106 hours). SurgCBVR comprises two tiers: Scene, retrieving the same operative state across cases and sites, and Workflow, retrieving and localizing phase transitions and deviations. Scene includes 74,765 clips spanning 40 classes, three temporal granularities, and three playback speeds; Workflow contains 1,724 transition clips. Fixed clip lengths and frame counts, together with phase-classifier oracle and duration-only baselines, help assess label and timing shortcuts. We evaluate six generic and surgical foundation models, two video retrieval methods, and contrastive heads trained on SurgCBVR, using within-dataset, cross-dataset, and pooled-gallery retrieval restricted to the same procedure type. Frozen representations barely outperform a timing-only baseline, transition retrieval approaches chance, and trained heads lose up to half their accuracy across datasets. These findings expose substantial limitations in current video representations and establish SurgCBVR as a benchmark for advancing surgery-aware retrieval.

## LusoClin: A Synthetic Clinical Note Dataset for Medical Information Retrieval in European Portuguese

DevFeed: [LusoClin: A Synthetic Clinical Note Dataset for Medical Information Retrieval in European Portuguese](<https://devfeed.tech/articles/lusoclin-a-synthetic-clinical-note-dataset-for-medical-information-retrieval-in-european-portuguese-142657.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23454>)

Author: Carla Teixeira Lopes, Daniel F\\'elix

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

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>), [AI-driven information retrieval](<https://devfeed.tech/topics/ai-driven-information-retrieval.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [lora](<https://devfeed.tech/topics/lora.md>), [llama](<https://devfeed.tech/topics/llama.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [managing large-scale text data in AI](<https://devfeed.tech/topics/managing-large-scale-text-data-in-ai.md>), [Open Source Models & Datasets](<https://devfeed.tech/topics/open-source-models-datasets.md>), [Internationalization (i18n)](<https://devfeed.tech/topics/i18n.md>)

Tags: [bert](<https://devfeed.tech/tags/bert.md>), [clinical-search](<https://devfeed.tech/tags/clinical-search.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [document-retrieval](<https://devfeed.tech/tags/document-retrieval.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [information-retrieval](<https://devfeed.tech/tags/information-retrieval.md>), [languages](<https://devfeed.tech/tags/languages.md>), [llama](<https://devfeed.tech/tags/llama.md>), [low-resource-languages](<https://devfeed.tech/tags/low-resource-languages.md>), [medical](<https://devfeed.tech/tags/medical.md>), [note](<https://devfeed.tech/tags/note.md>), [resource](<https://devfeed.tech/tags/resource.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>)

### AI overview

LusoClin is a publicly released dataset of synthetic clinical notes in European Portuguese, intended to support privacy-preserving research on clinical information retrieval in a language with limited access to real clinical text. It was created by preprocessing real clinical data, fine-tuning Llama 3.2 (3B) with Quantized Low-Rank Adaptation, and generating notes from prompts; a BERT-based model automatically annotates clinical entities for search and indexing. Evaluations using automatic metrics and human review indicate that the dataset captures relevant clinical language and may support document retrieval and domain-specific model adaptation. However, annotators can often distinguish its notes from real ones, and some medical inconsistencies remain.

### Source excerpt

arXiv:2611.23454v1 Announce Type: new Abstract: Access to large-scale clinical text collections is crucial for advancing medical information retrieval research, including clinical note search, patient cohort identification, and domain-adapted retrieval models. However, real clinical notes are rarely available due to privacy regulations, which particularly limits progress for low-resource languages such as European Portuguese. We present LusoClin, a publicly released dataset of synthetic clinical notes in European Portuguese, created to support privacy-preserving research on clinical text retrieval. LusoClin was generated by pre-processing real clinical data, fine-tuning the open-source Llama 3.2 (3B) instruction-tuned model using Quantized Low-Rank Adaptation, and applying prompt-based clinical note generation. To facilitate semantic indexing and clinical search, the notes are automatically annotated with clinical entities using a BERT-based model. We evaluate LusoClin in terms of utility, fidelity, diversity, and privacy using automatic metrics and human evaluation. Results indicate that the dataset captures clinically relevant language patterns and can support downstream IR applications such as clinical document retrieval and domain-specific model adaptation, although annotators can often distinguish synthetic from real notes and some medical inconsistencies persist.

## Retail Merchandising Principles for Web Designers and Developers: Display Design, Ranking Rules and Measurement

DevFeed: [Retail Merchandising Principles for Web Designers and Developers: Display Design, Ranking Rules and Measurement](<https://devfeed.tech/articles/retail-merchandising-principles-for-web-designers-and-developers-display-design-ranking-rules-and-measurement-141352.md>)

Original publisher: [Read original article](<https://www.sitepoint.com/retail-merchandising-principles-for-web-designers-and-developers-display-design-ranking-rules-and-measurement/>)

Author: Div John

Published: 2026-11-18T09:46:28Z

Content type: article

Language: en

Sources: [SitePoint](<https://devfeed.tech/sources/sitepoint.md>)

Topics: [web design](<https://devfeed.tech/topics/web-design.md>), [User interface design](<https://devfeed.tech/topics/ui-design.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [rule-engine](<https://devfeed.tech/topics/rule-engine.md>), [human centric design](<https://devfeed.tech/topics/human-centric-design.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [designer developer handoff](<https://devfeed.tech/topics/designer-developer-handoff.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [accessibility](<https://devfeed.tech/tags/accessibility.md>), [accessible](<https://devfeed.tech/tags/accessible.md>), [badge](<https://devfeed.tech/tags/badge.md>), [basics](<https://devfeed.tech/tags/basics.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [brand](<https://devfeed.tech/tags/brand.md>), [campaign](<https://devfeed.tech/tags/campaign.md>), [card](<https://devfeed.tech/tags/card.md>), [change](<https://devfeed.tech/tags/change.md>), [design](<https://devfeed.tech/tags/design.md>), [designers](<https://devfeed.tech/tags/designers.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [developers](<https://devfeed.tech/tags/developers.md>), [display](<https://devfeed.tech/tags/display.md>), [measurement](<https://devfeed.tech/tags/measurement.md>), [principles](<https://devfeed.tech/tags/principles.md>), [ranking](<https://devfeed.tech/tags/ranking.md>), [retail](<https://devfeed.tech/tags/retail.md>), [rules](<https://devfeed.tech/tags/rules.md>), [web](<https://devfeed.tech/tags/web.md>), [web-designers](<https://devfeed.tech/tags/web-designers.md>)

### AI overview

E-commerce merchandising works best when product visibility, ranking, accessibility and operational upkeep are treated as explicit interface rules. The article recommends curating the first screen, limiting visual emphasis, and encoding pins, boosts, brand caps and stock demotion in testable ranking logic; its Node.js example is a teaching sketch that omits production concerns such as personalization and search relevance. Price and badge colors should meet WCAG contrast thresholds, and promotions need start and end dates plus checks to prevent stale content. For layout changes, it demonstrates a two-proportion conversion test: illustrative results rise from 3.00% to 3.90% (z=2.21), while cautioning that this is not a general guarantee and assumes a preset sample size. Test one change with randomized comparable users, and coordinate design, engineering and operations so the shipped display matches the plan.

### Source excerpt

null Continue reading Retail Merchandising Principles for Web Designers and Developers: Display Design, Ranking Rules and Measurement on SitePoint.

## Efficient Generative Retrieval for E-commerce Search with Semantic Cluster IDs and Expert-Guided RL

DevFeed: [Efficient Generative Retrieval for E-commerce Search with Semantic Cluster IDs and Expert-Guided RL](<https://devfeed.tech/articles/efficient-generative-retrieval-for-e-commerce-search-with-semantic-cluster-ids-and-expert-guided-rl-139770.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.14434>)

Author: Jianbo Zhu, Xing Fang, Jing Wang, Mingmin Jin, Bokang Wang, Guangxin Song, Zhenyu Xie, Junjie Bai

Published: 2026-11-18T05:00:00Z

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>), [grpo](<https://devfeed.tech/topics/grpo.md>), [AI-driven information retrieval](<https://devfeed.tech/topics/ai-driven-information-retrieval.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [VAE](<https://devfeed.tech/topics/vae.md>)

Tags: [beam](<https://devfeed.tech/tags/beam.md>), [cluster](<https://devfeed.tech/tags/cluster.md>), [contrastive-learning](<https://devfeed.tech/tags/contrastive-learning.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [e-commerce](<https://devfeed.tech/tags/e-commerce.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generative](<https://devfeed.tech/tags/generative.md>), [group-relative-policy-optimization](<https://devfeed.tech/tags/group-relative-policy-optimization.md>), [grpo](<https://devfeed.tech/tags/grpo.md>), [ids](<https://devfeed.tech/tags/ids.md>), [learning](<https://devfeed.tech/tags/learning.md>), [offline](<https://devfeed.tech/tags/offline.md>), [online](<https://devfeed.tech/tags/online.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [performance](<https://devfeed.tech/tags/performance.md>), [policy](<https://devfeed.tech/tags/policy.md>), [production](<https://devfeed.tech/tags/production.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [rl](<https://devfeed.tech/tags/rl.md>), [search](<https://devfeed.tech/tags/search.md>), [semantic](<https://devfeed.tech/tags/semantic.md>)

### AI overview

The framework positions generative retrieval as a recall-stage supplement to existing e-commerce search, addressing catalog scale, latency, and downstream ranking alignment. CQ-SID combines category-aware and query-item contrastive learning with Residual Quantized VAEs to create hierarchical semantic IDs and reduce beam-search complexity. On TmallAPP search logs, it improves semantic and personalized click hitrate by up to 26.76% and 11.11% over RQ-VAE baselines while halving beam-search size. EG-GRPO uses ground-truth samples to stabilize reinforcement learning under sparse rewards and further improves multi-objective performance. Online A/B tests report GMV gains of 1.15% and UCTCVR gains of 0.40%; in production, the generative recall channel accounts for 50.25% of exposures, 58.96% of clicks, and 72.63% of purchases.

### Source excerpt

arXiv:2605.14434v2 Announce Type: replace-cross Abstract: Generative retrieval offers a promising alternative by unifying the fragmented multi-stage retrieval process into a single end-to-end model. However, its practical adoption in industrial e-commerce search remains challenging, given the massive and dynamic product catalogs, strict latency requirements, and the need to align retrieval with downstream ranking goals. In this work, we propose a retrieval framework tailored for real-world recall scenarios, positioning generative retrieval as a recall-stage supplement rather than an end-to-end replacement. Our method, CQ-SID (Category-and-Query constrained Semantic ID), employs category-aware and query-item contrastive learning along with Residual Quantized VAEs to encode items into hierarchical semantic cluster identifiers, significantly reducing beam search complexity. Additionally, we develop EG-GRPO (Expert-Guided Group Relative Policy Optimization), a reinforcement learning approach that aligns generative recall with downstream ranking under sparse rewards by injecting ground-truth samples to stabilize training. Offline experiments on TmallAPP search logs show that CQ-SID achieves up to 26.76% and 11.11% relative gains in semantic and personalized click hitrate over RQ-VAE baselines, while halving beam search size. EG-GRPO further improves multi-objective performance. Online A/B tests confirm gains in GMV (+1.15%) and UCTCVR (+0.40%). The generative recall channel now contributes substantially in production, accounting for over 50.25% of exposures, 58.96% of clicks, and 72.63% of purchases, demonstrating a viable path for deploying generative retrieval in real-world e-commerce systems.

## Fair Bubble Sort: Provably Optimal Fair Ranking with Continuous Sensitive Attributes

DevFeed: [Fair Bubble Sort: Provably Optimal Fair Ranking with Continuous Sensitive Attributes](<https://devfeed.tech/articles/fair-bubble-sort-provably-optimal-fair-ranking-with-continuous-sensitive-attributes-141770.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22352>)

Author: Antonio Ferrara, Fabio Vitale, Atsushi Miyauchi, Francesco Bonchi

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

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

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Combinatorial optimization](<https://devfeed.tech/topics/combinatorial-optimization.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>)

Tags: [algorithm](<https://devfeed.tech/tags/algorithm.md>), [continuous](<https://devfeed.tech/tags/continuous.md>), [cs-cy](<https://devfeed.tech/tags/cs-cy.md>), [cs-ds](<https://devfeed.tech/tags/cs-ds.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [fairness](<https://devfeed.tech/tags/fairness.md>), [ranking](<https://devfeed.tech/tags/ranking.md>), [sort](<https://devfeed.tech/tags/sort.md>)

### AI overview

Fair Bubble Sort (FBS) adjusts a score-based ranking for continuous sensitive attributes using targeted adjacent swaps, without first discretizing those attributes into groups. It aims to meet a prescribed Continuous Pairwise Parity (CPP) constraint, defined through Kendall correlation between ranking positions and the attribute, while minimizing Kemeny distance from the initial ranking. The paper claims exact optimality for unweighted Kemeny distance and approximation guarantees for the score-weighted setting; its running time depends on the number of swaps needed. Experiments on synthetic and real-world datasets reportedly find FBS scalable and better than discretization-based baselines on the fairness-accuracy Pareto front.

### Source excerpt

arXiv:2611.22352v1 Announce Type: new Abstract: Most fair-ranking methods assume categorical protected attributes, requiring continuous attributes such as age or income to be discretized into groups. This introduces arbitrary thresholds, loses fine-grained information, and ignores the natural ordering of the attribute. In this paper, we study the problem of fair ranking with continuous protected attributes without relying on thresholding. We introduce Continuous Pairwise Parity (CPP), a fairness notion based on Kendall correlation between ranking positions and the protected attribute, and seek rankings that satisfy a prescribed CPP constraint while minimizing their Kemeny distance from an initial score-based ranking. To solve this problem, we propose Fair Bubble Sort (FBS), an efficient post-processing algorithm based on targeted adjacent swaps. We prove that FBS is exactly optimal for the unweighted Kemeny distance and provide approximation guarantees for the score-weighted setting. FBS is output-sensitive, with running time determined by the number of swaps required to meet the fairness constraint. Experiments on synthetic and real-world datasets show that FBS is scalable and consistently outperforms discretization-based baselines, achieving a superior fairness-accuracy Pareto front.

## LoCaR: Localized Canvas Retrieval With Frozen Vision-Language Model

DevFeed: [LoCaR: Localized Canvas Retrieval With Frozen Vision-Language Model](<https://devfeed.tech/articles/locar-localized-canvas-retrieval-with-frozen-vision-language-model-139967.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22131>)

Author: Rahim Hossain, Dipanwita Saha, Ashirbad Mishra, Xinxin Shu, Svetlana Strunjas, Binbin Li

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

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

Topics: [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [AI-driven information retrieval](<https://devfeed.tech/topics/ai-driven-information-retrieval.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [region](<https://devfeed.tech/tags/region.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [vision-language-models](<https://devfeed.tech/tags/vision-language-models.md>)

### AI overview

LoCaR targets localized text-to-image retrieval queries that whole-image embeddings may miss when they concern small objects or local attributes. It uses SAM2 to propose object-focused regions and encodes each region independently with a frozen visual encoder, without training. An optional paired-support residual uses matched text-region exemplars without changing the encoders. The authors introduce LOCFG, a Visual Genome-derived benchmark for smaller, more challenging referents, and report across several vision-language backbones that better region representations are the main source of gains.

### Source excerpt

arXiv:2611.22131v1 Announce Type: new Abstract: Whole image embeddings can under represent small objects and local attributes that distinguish relevant images for localized queries. We present LoCaR, a training free framework for localized text to image retrieval with frozen vision language models. LoCaR constructs and utilizes independent proposals (SAM2) focusing on the object so as to get a more localized representation that independently encodes each region using the frozen visual encoder. We further study paired-support adaptation as an optional residual that uses matched text region exemplars without updating the underlying encoders. We also introduce LOCFG, a Visual Genome derived benchmark designed to evaluate localized retrieval for smaller and more challenging referents. Across several vision language backbones, our results show that improving the region representation itself is the main source of gain.

## Synergizing Evidence Retrieval and Utilization for Self-Improving Multimodal Scientific Document Reasoning

DevFeed: [Synergizing Evidence Retrieval and Utilization for Self-Improving Multimodal Scientific Document Reasoning](<https://devfeed.tech/articles/synergizing-evidence-retrieval-and-utilization-for-self-improving-multimodal-scientific-document-reasoning-140084.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22837>)

Author: Frank Nie, Ethan B. Liu, Yuan Zhu, Jindong Han

Published: 2026-11-18T05:00:00Z

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>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>), [AI-driven information retrieval](<https://devfeed.tech/topics/ai-driven-information-retrieval.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [acquisition](<https://devfeed.tech/tags/acquisition.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [budget](<https://devfeed.tech/tags/budget.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [framework](<https://devfeed.tech/tags/framework.md>), [grounded](<https://devfeed.tech/tags/grounded.md>), [guidance](<https://devfeed.tech/tags/guidance.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [ontology](<https://devfeed.tech/tags/ontology.md>), [optimize](<https://devfeed.tech/tags/optimize.md>), [organization](<https://devfeed.tech/tags/organization.md>), [question](<https://devfeed.tech/tags/question.md>), [questions](<https://devfeed.tech/tags/questions.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [reward](<https://devfeed.tech/tags/reward.md>), [settings](<https://devfeed.tech/tags/settings.md>), [sources](<https://devfeed.tech/tags/sources.md>), [space](<https://devfeed.tech/tags/space.md>), [tables](<https://devfeed.tech/tags/tables.md>)

### AI overview

The framework separates evidence retrieval from evidence use for multimodal scientific document reasoning. A Retriever selects source-aligned text, figure, and table evidence under a context budget; a Perceiver organizes selected evidence and the question into a question-conditioned latent ontology; and a Reasoner uses that guidance alongside the original sources to generate grounded answers. During training, the three components are alternately optimized with a shared answering reward. Retrieval Potential Feedback and Latent Efficacy Feedback diagnose whether questions need better retrieval or latent guidance and direct targeted resampling. Across four benchmarks and seven evaluation settings, it reports average scores of 69.9 with a 7B Reasoner and 75.0 with an 8B Reasoner, exceeding the strongest baseline by 4.0 and 9.1 points, respectively.

### Source excerpt

arXiv:2611.22837v1 Announce Type: new Abstract: Scientific document reasoning requires an agent to acquire and integrate evidence distributed across text, figures, and tables. Retrieval can identify relevant sources while missing complementary support, and answer-level feedback alone does not reveal whether an error stems from evidence acquisition or evidence use. We present an agentic Retriever--Perceiver--Reasoner framework for multimodal scientific document reasoning. The Retriever sequentially selects source-aligned evidence under a context budget. Given the selected evidence and question, the Perceiver constructs a question-conditioned latent ontology, an implicit organization of multimodal evidence in a shared continuous space. The Reasoner combines this latent guidance with the original sources to produce grounded answers. We train the three components through diagnostic-guided co-evolution: alternating updates optimize them with a shared answering reward, while Retrieval Potential Feedback (RPF) and Latent Efficacy Feedback (LEF) identify questions that need better retrieval or latent guidance and direct targeted resampling. Across four benchmarks and seven evaluation settings, our framework obtains average scores of 69.9 and 75.0 with 7B and 8B Reasoner backbones, exceeding the strongest baseline by 4.0 and 9.1 points, respectively.

## Improve search relevance with semantic reranking and BM25 score projection in Azure Cosmos DB

DevFeed: [Improve search relevance with semantic reranking and BM25 score projection in Azure Cosmos DB](<https://devfeed.tech/articles/improve-search-relevance-with-semantic-reranking-and-bm25-score-projection-in-azure-cosmos-db-139450.md>)

Original publisher: [Read original article](<https://devblogs.microsoft.com/cosmosdb/improve-search-relevance-with-semantic-reranking-and-bm25-score-projection-in-azure-cosmos-db/>)

Author: Madeline Egan

Published: 2026-11-17T18:45:12Z

Content type: release

Language: en

Sources: [Azure Cosmos DB Blog](<https://devfeed.tech/sources/azure-cosmos-db-blog.md>)

Topics: [AI-driven information retrieval](<https://devfeed.tech/topics/ai-driven-information-retrieval.md>), [hybrid-search](<https://devfeed.tech/topics/hybrid-search.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [Azure](<https://devfeed.tech/topics/azure.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-model](<https://devfeed.tech/tags/ai-model.md>), [azure](<https://devfeed.tech/tags/azure.md>), [azure-cosmos-db](<https://devfeed.tech/tags/azure-cosmos-db.md>), [azure-cosmos-db-for-nosql](<https://devfeed.tech/tags/azure-cosmos-db-for-nosql.md>), [bm25](<https://devfeed.tech/tags/bm25.md>), [full-text-search](<https://devfeed.tech/tags/full-text-search.md>), [projection](<https://devfeed.tech/tags/projection.md>), [ranking](<https://devfeed.tech/tags/ranking.md>), [relevance](<https://devfeed.tech/tags/relevance.md>), [reranker](<https://devfeed.tech/tags/reranker.md>), [reranking](<https://devfeed.tech/tags/reranking.md>), [score](<https://devfeed.tech/tags/score.md>), [search](<https://devfeed.tech/tags/search.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [text](<https://devfeed.tech/tags/text.md>)

### AI overview

Azure Cosmos DB adds two generally available search capabilities: a semantic reranker and full-text score projection. The reranker uses an AI model to reorder retrieved candidates by relevance to a query or task context, which the excerpt recommends considering for natural-language queries, RAG, and hybrid retrieval. Setup includes enabling the account feature, granting the calling identity the Semantic Reranker User role, using Microsoft Entra ID credentials, and sending retrieved candidates to the rerank call. Because reranking adds an inference call, evaluate relevance gains against increased latency and cost. Score projection exposes ranking scores in query output for inspection, thresholding, and debugging. The excerpt also lists additional full-text search features as planned for early 2027.

### Source excerpt

At Ignite 2026 on November 17, we are announcing two generally available capabilities in Azure Cosmos DB to help you build better search experiences: Semantic reranker in Azure Cosmos DB Score projection for full-text ranking These capabilities let you improve result quality and make ranking behavior easier to inspect and tune. Semantic reranker in Azure [...] The post Improve search relevance with semantic reranking and BM25 score projection in Azure Cosmos DB appeared first on Azure Cosmos DB Blog.

## Simplify AI retrieval with embedding generation using Microsoft-Embedding-1

DevFeed: [Simplify AI retrieval with embedding generation using Microsoft-Embedding-1](<https://devfeed.tech/articles/simplify-ai-retrieval-with-embedding-generation-using-microsoft-embedding-1-139451.md>)

Original publisher: [Read original article](<https://devblogs.microsoft.com/cosmosdb/microsoft-embedding-one/>)

Author: Khelan Modi

Published: 2026-11-17T18:45:11Z

Content type: release

Language: en

Sources: [Azure Cosmos DB Blog](<https://devfeed.tech/sources/azure-cosmos-db-blog.md>)

Topics: [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [Vectors & LLMs](<https://devfeed.tech/topics/vectors-llms.md>), [AI-driven information retrieval](<https://devfeed.tech/topics/ai-driven-information-retrieval.md>), [Azure](<https://devfeed.tech/topics/azure.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [analyst](<https://devfeed.tech/tags/analyst.md>), [azure](<https://devfeed.tech/tags/azure.md>), [azure-cosmos-db](<https://devfeed.tech/tags/azure-cosmos-db.md>), [charts](<https://devfeed.tech/tags/charts.md>), [cosmos](<https://devfeed.tech/tags/cosmos.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [financial](<https://devfeed.tech/tags/financial.md>), [generation](<https://devfeed.tech/tags/generation.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [pages](<https://devfeed.tech/tags/pages.md>), [q3](<https://devfeed.tech/tags/q3.md>), [region](<https://devfeed.tech/tags/region.md>), [reports](<https://devfeed.tech/tags/reports.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [revenue](<https://devfeed.tech/tags/revenue.md>), [search](<https://devfeed.tech/tags/search.md>), [tables](<https://devfeed.tech/tags/tables.md>)

### AI overview

Microsoft Embedding 1 creates embeddings for text, images, and document pages in a shared vector space, allowing text queries to retrieve answers in charts, diagrams, and scanned files. The source reports a #1 ranking in its ViDoRe v3 size class (66.24 nDCG@10, as of November 16, 2026). It offers dense and late-interaction multi-vector output: multi-vector retrieval improves visual-document relevance, but can use substantial storage and requires MaxSim scoring. Users can limit vector count and dimensions; 32 vectors of 128 dimensions reportedly gives up about 3.4 nDCG@10 points while reducing storage roughly 300-fold versus unconstrained output. Dense vectors are positioned for text-heavy content, multi-vector for visual documents. The article describes enabling inference on a Cosmos DB account, generating embeddings with preview Python or .NET clients, then storing and searching vectors; input tokens are billed. It says text retrieval scores on par with text-embedding-3-large on BEIR, with smaller vectors, while benchmark results and claims are source-reported.

### Source excerpt

Most enterprise knowledge doesn't live in clean text. It lives in charts, tables, scanned pages, and diagrams, where text-only search often misses it: Financial reports: An analyst asks, "Which region's revenue fell in Q3?" The answer is a bar in a chart on page 14, and no sentence on the page says it. Technical manuals: A [...] The post Simplify AI retrieval with embedding generation using Microsoft-Embedding-1 appeared first on Azure Cosmos DB Blog.

## UniGraph: A Unified Graph-based Index for Dynamic Hybrid Dense-Sparse Vector Retrieval

DevFeed: [UniGraph: A Unified Graph-based Index for Dynamic Hybrid Dense-Sparse Vector Retrieval](<https://devfeed.tech/articles/unigraph-a-unified-graph-based-index-for-dynamic-hybrid-dense-sparse-vector-retrieval-138301.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20758>)

Author: Keyu Chen, Xiaoyao Zhong, Jiabao Jin, Peng Cheng, Wangze Ni, Jingkuan Song, Heng Tao Shen

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

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

Topics: [hybrid-search](<https://devfeed.tech/topics/hybrid-search.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [bounded](<https://devfeed.tech/tags/bounded.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [graph](<https://devfeed.tech/tags/graph.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [hybrid-graph](<https://devfeed.tech/tags/hybrid-graph.md>), [index](<https://devfeed.tech/tags/index.md>), [lexical](<https://devfeed.tech/tags/lexical.md>), [multiple](<https://devfeed.tech/tags/multiple.md>), [production](<https://devfeed.tech/tags/production.md>), [pruning](<https://devfeed.tech/tags/pruning.md>), [query](<https://devfeed.tech/tags/query.md>), [recall](<https://devfeed.tech/tags/recall.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [scale](<https://devfeed.tech/tags/scale.md>), [search](<https://devfeed.tech/tags/search.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [separate](<https://devfeed.tech/tags/separate.md>), [static](<https://devfeed.tech/tags/static.md>), [vector](<https://devfeed.tech/tags/vector.md>)

### AI overview

UniGraph combines neighbor sets built at multiple dense-sparse hybrid weights into one bounded-degree graph, allowing query-specific weights without rebuilding the index. Its adaptive search selects a sparse- or dense-guided entry point based on the query weight, and dense-first pruning avoids some exact sparse-distance computations. The abstract says that in mixed-weight experiments, UniGraph achieved 27.6%-52.3% higher QPS than the fastest baseline on each dataset at Recall@100 >= 0.95, with a favorable Recall-QPS trade-off across weights. It also reports deployment at scale in Ant Group's production environment.

### Source excerpt

arXiv:2611.20758v1 Announce Type: cross Abstract: Hybrid dense-sparse vector retrieval combines semantic signals from dense representations with lexical signals from sparse representations, typically ranking items by a query-dependent weighted sum of dense and sparse vector distances. Existing systems commonly search separate dense and sparse vector indexes and rerank the union of their candidates, incurring two retrieval passes and potentially discarding items that rank highly only after the semantic and lexical signals are combined. Constructing a graph-based index directly under a hybrid distance can mitigate this premature candidate loss. However, because varying the hybrid weight alters the underlying neighborhood relationships, a single static graph built at a fixed weight cannot accommodate dynamic query-specific weights. Therefore, we propose a Unified Hybrid Graph (UniGraph), which merges neighbor sets computed at multiple hybrid weights into a single bounded-degree graph index, enabling hybrid vector retrieval with different query-specific weights without index reconstruction. We further develop an adaptive weight-guided search framework that chooses between sparse- and dense-guided entry points according to the query weight, together with a dense-first hybrid distance pruning strategy that avoids unnecessary exact sparse distance computations. Extensive experiments show that UniGraph provides a favorable Recall-QPS trade-off across different query weights. In the mixed-weight setting, UniGraph delivers 27.6%~52.3% higher QPS than the fastest baseline on each dataset at Recall@100 greater than or equal to 0.95. UniGraph has been deployed at scale in Ant Group's production environment, where hybrid retrieval with query-dependent weights is in strong demand.

## Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging

DevFeed: [Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging](<https://devfeed.tech/articles/scaling-retrieval-augmented-reasoning-with-parallel-search-and-explicit-merging-137255.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.13534>)

Author: Jiabei Liu, Wenyu Mao, Junfei Tan, Chunxu Shen, Lingling Yi, Jiancan Wu, Xiang Wang

Published: 2026-11-17T05:00:00Z

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>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [information](<https://devfeed.tech/tags/information.md>), [parallel](<https://devfeed.tech/tags/parallel.md>), [performance](<https://devfeed.tech/tags/performance.md>), [queries](<https://devfeed.tech/tags/queries.md>), [question](<https://devfeed.tech/tags/question.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [search](<https://devfeed.tech/tags/search.md>), [snr](<https://devfeed.tech/tags/snr.md>)

### AI overview

MultiSearch aims to improve retrieval-augmented reasoning by replacing a single query per reasoning step with parallel queries from multiple perspectives, then explicitly consolidating and refining the retrieved information. The authors say this broadens coverage, reduces reliance on any one retrieval result, and improves the search signal-to-noise ratio. Their reinforcement learning framework uses separate process rewards to optimize both multi-query retrieval and information consolidation. The abstract reports better retrieval signal-to-noise and question-answering performance than baseline methods across seven benchmarks; it does not provide benchmark names or quantitative results.

### Source excerpt

arXiv:2605.13534v2 Announce Type: replace Abstract: Deep search agents have proven effective in enhancing LLMs by retrieving external knowledge during multi-step reasoning. However, existing methods often generate a single query for retrieval at each reasoning step, limiting information coverage and introducing high noise. This may result in low signal-to-noise ratios (SNR) during search, degrading reasoning accuracy and leading to unnecessary reasoning steps. In this paper, we introduce MultiSearch, an RL-based framework that addresses these limitations through multi-query retrieval and explicit merging of retrieved information. At each reasoning step, MultiSearch generates queries from multiple perspectives and retrieves external information in parallel, expanding the scope of relevant information and mitigating the reliance on any single retrieval result. Then, the agent consolidates and refines retrieved information at the merging process, improving the SNR and ensuring more accurate reasoning. Additionally, we propose a reinforcement learning framework with a multi-process reward design to optimize agents for both multi-query retrieval and information consolidation. Extensive experiments on seven benchmarks demonstrate that MultiSearch outperforms baseline methods, enhancing the SNR of retrieval and improving reasoning performance in question-answering tasks.

## CLEAR: Legible and Steerable Recommendation via Grounded Natural-Language Interests

DevFeed: [CLEAR: Legible and Steerable Recommendation via Grounded Natural-Language Interests](<https://devfeed.tech/articles/clear-legible-and-steerable-recommendation-via-grounded-natural-language-interests-137395.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.19110>)

Author: Qi Guo, Reza Mirghaderi, Iordanis Fostiropoulos, David Fan, Yuchen Liu, Shiliang Tang, Lukasz Korycki, Golnaz Ghasemiesfeh, Xinzhu Bei, Sasha Vorontsov, Hanchao Yu, Brendan Quinlivan, Khoi Pham, Jigar

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

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

Topics: [personalization](<https://devfeed.tech/topics/personalization.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Instagram](<https://devfeed.tech/topics/instagram.md>)

Tags: [ablation](<https://devfeed.tech/tags/ablation.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [delivery](<https://devfeed.tech/tags/delivery.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [facebook](<https://devfeed.tech/tags/facebook.md>), [grounded](<https://devfeed.tech/tags/grounded.md>), [grounding](<https://devfeed.tech/tags/grounding.md>), [natural-language](<https://devfeed.tech/tags/natural-language.md>), [production](<https://devfeed.tech/tags/production.md>), [ranking](<https://devfeed.tech/tags/ranking.md>), [recommendation](<https://devfeed.tech/tags/recommendation.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>)

### AI overview

CLEAR makes recommendation preferences editable by representing them as readable natural-language interests. Users can accept or suppress interests as authoritative preference state, and inferred interests are grounded in supporting events from their history. Each interest also connects to serving: labels and profile-conditioned rewrites support lexical retrieval, events support behavioral retrieval, and an embedding projection supports vector retrieval; stable identities enable ranking, attribution, and exposure control. Newly declared interests can enter before behavioral evidence exists, initially drawing candidates from topical retrieval. In reported results, users rated about 88.5% of displayed interests accurate. The Specialized 3B generator scored 0.3967 mean-user F1@10, versus 0.3633 for Gemini 2.5 Pro and 0.1911 for the prior generator. A cumulative user-randomized ablation found same-day delivery losses of 8.7, 11.1, and 13.7 percentage points when removing, respectively, added-interest ranking terms, reserved top-slot insertion, and interest-conditioned candidate sourcing; these results depend on the tested removal sequence. CLEAR components have operated for over a year

### Source excerpt

arXiv:2611.19110v1 Announce Type: new Abstract: Modern recommenders keep learned preferences in representations people cannot inspect or change. We present CLEAR (Controllable and Legible End-to-end Architecture for Recommendation), an end-to-end system deployed at Meta and built around an editable natural-language interest layer. CLEAR makes a ranked subset of inferred interests readable and stores accepted additions and suppressions as authoritative preference state. Behavioral grounding maps each inferred interest back to supporting events in the user's own history. The resulting interest object is also a serving address: its label and profile-conditioned rewrites drive lexical retrieval, its supporting events seed behavioral retrieval, its projection queries an embedding index, and its stable identity supports ranking, attribution, and exposure control. A fresh user declaration may precede behavioral support, so it enters through the same serving identity and initially draws candidates from topical retrieval. Ranking makes those candidates competitive, while a delivery controller observes attributable exposure and replenishes underexposed interests. Direct user review found that users rated about 88.5% of displayed interests accurate. In an offline benchmark using a shared evaluation protocol, the Specialized 3B generator reached 0.3967 mean-user F1@10, compared with 0.3633 for Gemini 2.5 Pro and 0.1911 for the prior generator. For a newly declared interest, a user-randomized cumulative ablation measured same-day delivery losses of 8.7 percentage points for added-interest ranking terms, 11.1 for reserved top-slot insertion, and 13.7 for interest-conditioned candidate sourcing, conditional on the tested removal sequence. CLEAR components have operated in production for over one year; the system spans four surfaces on Instagram and Facebook, with an interest layer people can inspect, correct, and use to direct recommendations.

## Get answers from tables with tabular search in Amazon Bedrock Managed Knowledge Base

DevFeed: [Get answers from tables with tabular search in Amazon Bedrock Managed Knowledge Base](<https://devfeed.tech/articles/get-answers-from-tables-with-tabular-search-in-amazon-bedrock-managed-knowledge-base-136121.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/get-answers-from-tables-with-tabular-search-in-amazon-bedrock-managed-knowledge-base/>)

Author: Josh DeMuth

Published: 2026-11-16T16:12:16Z

Content type: tutorial

Language: en

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

Topics: [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [CSV](<https://devfeed.tech/topics/csv.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>)

Tags: [agentic-retrieval](<https://devfeed.tech/tags/agentic-retrieval.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-knowledge-bases](<https://devfeed.tech/tags/amazon-bedrock-knowledge-bases.md>), [amazon-s3](<https://devfeed.tech/tags/amazon-s3.md>), [atlassian-confluence](<https://devfeed.tech/tags/atlassian-confluence.md>), [aws-cdk](<https://devfeed.tech/tags/aws-cdk.md>), [aws-cli](<https://devfeed.tech/tags/aws-cli.md>), [aws-identity-and-access-management-iam](<https://devfeed.tech/tags/aws-identity-and-access-management-iam.md>), [aws-sdk](<https://devfeed.tech/tags/aws-sdk.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [bi](<https://devfeed.tech/tags/bi.md>), [bi-tools](<https://devfeed.tech/tags/bi-tools.md>), [csv](<https://devfeed.tech/tags/csv.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [tables](<https://devfeed.tech/tags/tables.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>)

### AI overview

Amazon Bedrock Managed Knowledge Base tabular search lets agentic retrieval calculate over full CSV and Excel tables and combine those results with retrieved documents in one AgenticRetrieveStream request. It stages original files in an isolated, network-free sandbox, runs model-written code, and returns printed results for the agent's cited answer. In the finance example, it applies policy rules and memo revisions to workbook data to identify departments requiring variance commentary. Plain Retrieve returns passages without running code; tabular search adds an agent turn and latency. It is intended for table lookups and calculations, while governed metrics, recurring dashboards, warehouse-scale joins, and reporting controls remain suited to BI tools. File types, size limits, caller permissions, and retrieval's choice of workbook affect whether it can operate; traces identify files read, but do not expose generated code.

### Source excerpt

Amazon Bedrock Managed Knowledge Base now supports tabular search, so agentic retrieval can answer questions over CSV, XLSX, and XLS files. It looks up values and runs calculations across every relevant row, then combines the results with facts from related documents to answer multi-step analytical questions.

## Explanations that Transfer: Interpreting Medical Retrieval with Sparse AutoEncoders

DevFeed: [Explanations that Transfer: Interpreting Medical Retrieval with Sparse AutoEncoders](<https://devfeed.tech/articles/explanations-that-transfer-interpreting-medical-retrieval-with-sparse-autoencoders-135876.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.18179>)

Author: Diane Bouchacourt, Ga\\"etan Brison

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

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

Topics: [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [autoencoders](<https://devfeed.tech/tags/autoencoders.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [domain](<https://devfeed.tech/tags/domain.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embedding-models](<https://devfeed.tech/tags/embedding-models.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [features](<https://devfeed.tech/tags/features.md>), [finetuning](<https://devfeed.tech/tags/finetuning.md>), [information-retrieval](<https://devfeed.tech/tags/information-retrieval.md>), [medical](<https://devfeed.tech/tags/medical.md>), [medical-ai](<https://devfeed.tech/tags/medical-ai.md>), [relevance](<https://devfeed.tech/tags/relevance.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [retrieval-systems](<https://devfeed.tech/tags/retrieval-systems.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [systems](<https://devfeed.tech/tags/systems.md>)

### AI overview

The paper applies sparse autoencoders to make medical retrieval embeddings more interpretable while preserving query-document relevance through a reconstruction objective and InfoNCE contrastive loss. Across three embedding models and six medical retrieval datasets, sparse codes trained on a medical corpus improve in-domain retrieval over the original embeddings and lose less performance out of domain, especially on corpora distant from training. Features are interpreted from the queries and documents that activate them, offering clues to why documents are retrieved; the abstract reports that these interpretations also transfer beyond the training distribution.

### Source excerpt

arXiv:2611.18179v1 Announce Type: cross Abstract: Medical AI systems that answer users' queries rely on retrieving medical knowledge from large document collections. In this context, finetuning general models on medical datasets can improve retrieval relevance. Yet the dense embeddings underlying modern retrieval systems remain largely opaque, making it difficult to understand the mechanics behind their results. Moreover, adapting to a specific medical dataset risks losing transferability to new clinical corpora. In this work, we tackle these issues by applying Sparse Autoencoders (SAEs) to medical information retrieval, transforming dense text embeddings into semantically interpretable representations. To do so, our model combines a reconstruction objective with an InfoNCE contrastive loss that directly preserves query-document relevance. We evaluate three embedding models across six medical retrieval datasets, both in-domain and out-of-domain. Trained on a medical corpus, our sparse codes improve in-domain retrieval over the original embeddings, and lose less out-of-domain performance than their dense counterparts, especially when the target corpus is distant from the training one. Importantly, our experiments show that the method yields interpretable features whose semantic content can be inferred from the queries and documents that activate them most strongly. The interpretation of these features sheds light on why a particular document was retrieved, and transfers beyond the training distribution.

## Beyond Bot Labels: Retrospective Consequence-Grounded Ranking of Attributed Cache Harm in E-Commerce Logs

DevFeed: [Beyond Bot Labels: Retrospective Consequence-Grounded Ranking of Attributed Cache Harm in E-Commerce Logs](<https://devfeed.tech/articles/beyond-bot-labels-retrospective-consequence-grounded-ranking-of-attributed-cache-harm-in-e-commerce-logs-134920.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.18027>)

Author: Jisoo Kim, Youngwoo Seo, Seonghoon Jeong

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>), [arXiv: Networking](<https://devfeed.tech/sources/arxiv-networking.md>)

Topics: [Cache](<https://devfeed.tech/topics/cache.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [after](<https://devfeed.tech/tags/after.md>), [agent](<https://devfeed.tech/tags/agent.md>), [also](<https://devfeed.tech/tags/also.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [attribution](<https://devfeed.tech/tags/attribution.md>), [audits](<https://devfeed.tech/tags/audits.md>), [automated](<https://devfeed.tech/tags/automated.md>), [automated-traffic](<https://devfeed.tech/tags/automated-traffic.md>), [automation](<https://devfeed.tech/tags/automation.md>), [based](<https://devfeed.tech/tags/based.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [bot](<https://devfeed.tech/tags/bot.md>), [cache](<https://devfeed.tech/tags/cache.md>), [commerce](<https://devfeed.tech/tags/commerce.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ni](<https://devfeed.tech/tags/cs-ni.md>), [e-commerce](<https://devfeed.tech/tags/e-commerce.md>), [grounded](<https://devfeed.tech/tags/grounded.md>), [logs](<https://devfeed.tech/tags/logs.md>), [ranking](<https://devfeed.tech/tags/ranking.md>), [retrospective](<https://devfeed.tech/tags/retrospective.md>)

### AI overview

The study ranks sessions by the cache harm they cause: chronological replay attributes each eviction-induced miss affecting a protected shopping session to the session whose insertion last evicted the object, and a behavioral model predicts harmful sessions. Selected sessions bypass the cache while still receiving origin service. In a 12.7-million-request trace, the top 1% accounted for 48.8% of attributed harm; sessions without bot tags contributed 49.1% of that tier's harm. At a 20% request-volume target, the default conditional cache-hit-ratio difference reached 93% of the User-Agent baseline while selecting 47 times fewer sessions. The authors note this comparison conditions on remaining victims and also report victim bypass. A 539-session check found attribution order correlated with victim-hit changes after removal (Spearman 0.80); replay and retraining on a second store reproduced the concentration pattern.

### Source excerpt

arXiv:2611.18027v1 Announce Type: cross Abstract: Web caches reduce origin load and latency, but automated traffic can either warm them or evict objects shoppers reuse, lowering the cache hit ratio (CHR). Existing bot defenses generally infer automation from User-Agent (UA) strings or behavior rather than identify sessions that impose cross-session cache harm. We instead formulate the task as ranking sessions by eviction damage and propose consequence-grounded session ranking. A single chronological replay attributes each eviction-induced miss by a protected shopping session (a victim) to the session whose insertion last evicted the object. A behavioral model predicts the target from session behavior alone. Selected sessions bypass the cache but remain origin-served. In a controlled check of 539 non-victim sessions selected across harm levels, attribution order tracks victim-hit changes after removal (Spearman correlation 0.80). On a 12.7-million-request real trace, the top 1% of sessions carry 48.8% of attributed harm. Sessions without bot tags contribute 49.1% of this tier's harm. At the 20% request-volume target, the default conditional CHR difference reaches 93% of the UA baseline, which selects 47 times as many sessions. Six training seeds show little variation. This comparison conditions on the victims that remain, so we also report victim bypass. Local replay and retraining on a second store reproduce harm concentration and a top tier dominated by sessions without bot tags. These results establish attributed cross-session harm as an outcome-based target for retrospective cache audits and selective intervention design.

## Introducing agent-ready schemas

DevFeed: [Introducing agent-ready schemas](<https://devfeed.tech/articles/introducing-agent-ready-schemas-136189.md>)

Original publisher: [Read original article](<https://blog.vespa.ai/introducing-agent-ready-schemas/>)

Author: bratseth ingrid

Published: 2026-11-16T00:00:00Z

Content type: article

Language: en

Sources: [Vespa Blog](<https://devfeed.tech/sources/vespa-blog.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>)

Tags: [2015](<https://devfeed.tech/tags/2015.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [added](<https://devfeed.tech/tags/added.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-discovery](<https://devfeed.tech/tags/agent-discovery.md>), [agents](<https://devfeed.tech/tags/agents.md>), [all](<https://devfeed.tech/tags/all.md>), [allows](<https://devfeed.tech/tags/allows.md>), [also](<https://devfeed.tech/tags/also.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [apis](<https://devfeed.tech/tags/apis.md>), [can](<https://devfeed.tech/tags/can.md>), [experts](<https://devfeed.tech/tags/experts.md>), [information](<https://devfeed.tech/tags/information.md>), [like](<https://devfeed.tech/tags/like.md>), [need](<https://devfeed.tech/tags/need.md>), [schemas](<https://devfeed.tech/tags/schemas.md>), [search](<https://devfeed.tech/tags/search.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

Vespa 8.786.55 and later can generate agent guidance from application schemas and expose it at a container's /skills/v1/ endpoint when <skills><schemas/></skills> is enabled. Authors can add explanation blocks to describe data conventions, fields, and rank profiles; these are included and kept aligned with schema changes. In reported evaluations with Claude Sonnet 5.5, explanations raised one-shot accuracy on data-dependent tasks from 9% to 93%. In iterative tasks, the full skill used a quarter as many queries, 30% less model time, and 40% fewer tokens while improving correctness. On STaRK-Amazon, it increased MRR by 12% and reduced token cost by 68% versus an agent without the skill. Results are from the described datasets and setups; the excerpt does not establish performance beyond them.

### Source excerpt

Agents need information to work, and they can search like experts to get it. Agent-ready schemas tell them how.

## Web search for agents is here: Why ranking still decides the answer

DevFeed: [Web search for agents is here: Why ranking still decides the answer](<https://devfeed.tech/articles/web-search-for-agents-is-here-why-ranking-still-decides-the-answer-134078.md>)

Original publisher: [Read original article](<https://thenewstack.io/ai-agent-search-ranking/>)

Author: Bonnie Chase

Published: 2026-11-14T16:00:00Z

Content type: article

Language: en

Sources: [The New Stack](<https://devfeed.tech/sources/the-new-stack.md>)

Topics: [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [search-engines](<https://devfeed.tech/topics/search-engines.md>), [hybrid-search](<https://devfeed.tech/topics/hybrid-search.md>), [AI-driven information retrieval](<https://devfeed.tech/topics/ai-driven-information-retrieval.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Web](<https://devfeed.tech/topics/web.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [22](<https://devfeed.tech/tags/22.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [access-controls](<https://devfeed.tech/tags/access-controls.md>), [account](<https://devfeed.tech/tags/account.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-engineering](<https://devfeed.tech/tags/ai-engineering.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [but](<https://devfeed.tech/tags/but.md>), [first](<https://devfeed.tech/tags/first.md>), [here](<https://devfeed.tech/tags/here.md>), [information](<https://devfeed.tech/tags/information.md>), [needs](<https://devfeed.tech/tags/needs.md>), [post-contributed](<https://devfeed.tech/tags/post-contributed.md>), [ranking](<https://devfeed.tech/tags/ranking.md>), [search](<https://devfeed.tech/tags/search.md>), [sponsor-vespa-ai](<https://devfeed.tech/tags/sponsor-vespa-ai.md>), [sponsored-post-contributed](<https://devfeed.tech/tags/sponsored-post-contributed.md>), [url](<https://devfeed.tech/tags/url.md>), [vespa-ai](<https://devfeed.tech/tags/vespa-ai.md>), [web](<https://devfeed.tech/tags/web.md>), [web-search](<https://devfeed.tech/tags/web-search.md>)

### AI overview

Live web search helps agents find current pages, but a retrieval layer must decide which web and internal evidence to trust and show. The article warns that simply concatenating results can leave conflicts unresolved, favor stale but similar documents, expose restricted content if permissions are checked too late, and increase cost and latency across repeated agent calls. It recommends combining keyword, vector, and structured filtering; ranking with explicit freshness, source authority, and business rules; enforcing permissions at query time; and sending only relevant passages to the model. External results can be indexed with internal data when permitted or kept separate and fused or reranked later; these choices trade off latency, freshness, score comparability, and complexity. The article also advises measuring retrieval quality separately from answer generation and load-testing at realistic agent call volumes.

### Source excerpt

AI agents have had a URL problem for a while. When an agent needs current information but has no search The post Web search for agents is here: Why ranking still decides the answer appeared first on The New Stack.

## Perplexity Releases Decider v1.3: Open-Weight Decision Models Add Locate

DevFeed: [Perplexity Releases Decider v1.3: Open-Weight Decision Models Add Locate](<https://devfeed.tech/articles/perplexity-releases-decider-v1-3-open-weight-decision-models-add-locate-132437.md>)

Original publisher: [Read original article](<https://www.marktechpost.com/2026/11/13/perplexity-decider-v1-3-open-weight-decision-models-locate/>)

Author: Asif Razzaq

Published: 2026-11-13T16:10:02Z

Content type: news

Language: en

Sources: [MarkTechPost](<https://devfeed.tech/sources/marktechpost.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Model Development](<https://devfeed.tech/topics/model-development.md>), [Open Source Models & Datasets](<https://devfeed.tech/topics/open-source-models-datasets.md>), [releases](<https://devfeed.tech/topics/releases.md>), [hugging face](<https://devfeed.tech/topics/hugging-face.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [API Business Models](<https://devfeed.tech/topics/api-business-models.md>)

Tags: [1-3](<https://devfeed.tech/tags/1-3.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai-shorts](<https://devfeed.tech/tags/ai-shorts.md>), [applications](<https://devfeed.tech/tags/applications.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [classification](<https://devfeed.tech/tags/classification.md>), [decision-models](<https://devfeed.tech/tags/decision-models.md>), [decisions-api](<https://devfeed.tech/tags/decisions-api.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [editors-pick](<https://devfeed.tech/tags/editors-pick.md>), [for-devs](<https://devfeed.tech/tags/for-devs.md>), [harness](<https://devfeed.tech/tags/harness.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [new-releases](<https://devfeed.tech/tags/new-releases.md>), [open](<https://devfeed.tech/tags/open.md>), [perplexity](<https://devfeed.tech/tags/perplexity.md>), [span](<https://devfeed.tech/tags/span.md>), [staff](<https://devfeed.tech/tags/staff.md>), [tech-news](<https://devfeed.tech/tags/tech-news.md>), [technology](<https://devfeed.tech/tags/technology.md>), [weight](<https://devfeed.tech/tags/weight.md>)

### AI overview

Perplexity's Decider v1.3 models return option probabilities for classification and scoring rather than generated text. The main addition is Locate, which extracts text spans with character offsets for requested fields; it uses a span head and LoRA adapter while keeping the decision head and backbone frozen. In Perplexity's self-reported results, v1.3 reached 91.6% mean accuracy across 63 query-classification tasks, while Locate averaged 69.0 across 17 out-of-domain tasks. The excerpt also reports 0.27% answer flips under reorder or relabel transformations. Weights are available under Apache 2.0; the API costs $0.02 per million input tokens for v1.3 and $0.01 for Flash, with output free. Local deployment requires about 49 GiB of BF16 weights for v1.3 or 8.5 GiB for Flash; no quantized variants are reported. The benchmark figures are Perplexity's own, and Flash trails Jev 1.14 in finance, programming, and law.

### Source excerpt

Perplexity Decider v1.3 and Flash v1.3 are open-weight decision models that return probabilities, not text. Version 1.3 adds Locate for span extraction and reports 91.6% mean accuracy on 63 query-classification tasks. The post Perplexity Releases Decider v1.3: Open-Weight Decision Models Add Locate appeared first on MarkTechPost.

[Next page](<https://devfeed.tech/topics/information-retrieval.md?cursor=WyIyMDI2LTExLTEzVDE2OjEwOjAyKzAwOjAwIiwgIjQxZGVmMDliLTI1NDUtNDBlMS1iNTgxLWQ5NzA4NWFiY2IyOSJd>)