# AI Context Management

AI context management is the practice of deciding what an AI system remembers, retrieves, and forwards into each model call so that multi-turn conversations stay coherent.

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

## Automate the Status Update, Not the Conversation

DevFeed: [Automate the Status Update, Not the Conversation](<https://devfeed.tech/articles/automate-the-status-update-not-the-conversation-146578.md>)

Original publisher: [Read original article](<https://swamp-club.com/feed/p/fa87e965-c1d9-4363-b828-a3a51d09a425/go>)

Author: jpisgeek

Published: 2026-11-20T14:57:52Z

Content type: article

Language: en

Sources: [Swamp Club Feed](<https://devfeed.tech/sources/swamp-club-feed.md>)

Topics: [AI for data automation](<https://devfeed.tech/topics/ai-for-data-automation.md>), [agent to agent communication](<https://devfeed.tech/topics/agent-to-agent-communication.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [rachels-ramblings](<https://devfeed.tech/topics/rachels-ramblings.md>)

Tags: [agent-workflows](<https://devfeed.tech/tags/agent-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [automate](<https://devfeed.tech/tags/automate.md>), [azure](<https://devfeed.tech/tags/azure.md>), [azure-devops](<https://devfeed.tech/tags/azure-devops.md>), [clickup](<https://devfeed.tech/tags/clickup.md>), [dashboard](<https://devfeed.tech/tags/dashboard.md>), [dashboards](<https://devfeed.tech/tags/dashboards.md>), [discord](<https://devfeed.tech/tags/discord.md>), [docs](<https://devfeed.tech/tags/docs.md>), [drop-in](<https://devfeed.tech/tags/drop-in.md>), [files](<https://devfeed.tech/tags/files.md>), [fleet](<https://devfeed.tech/tags/fleet.md>), [github](<https://devfeed.tech/tags/github.md>), [know](<https://devfeed.tech/tags/know.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [status](<https://devfeed.tech/tags/status.md>), [talk](<https://devfeed.tech/tags/talk.md>), [time](<https://devfeed.tech/tags/time.md>), [update](<https://devfeed.tech/tags/update.md>)

### AI overview

The author wants agents to make project catch-up self-service so team conversations can focus on difficult decisions. Existing agents update multiple tools, but coworkers still have to check them and piece together changes; shared notes or a docs repository help preserve and exchange information, yet still require syncing and review. The proposed starting point is one project and one question: can a teammate learn what changed since yesterday without asking the author to reconcile several sources? Answers should identify what changed and when, link to supporting tickets or runs, and disclose stale information or uncertainty. The examples show why: a VM build reported "WORKGROUP joined" despite a successful domain join, and a dashboard that reports only the last healthy check-in can conceal a later failed attempt. The team approach remains unproven; the author suggests seeing whether better-prepared calls make room for substantive discussion.

### Source excerpt

What if agents handled the catch-up, and we used that time to talk about the hard stuff?

## Some Memories Must Fade: Persistence and Decay of User Memories in Model Parameters

DevFeed: [Some Memories Must Fade: Persistence and Decay of User Memories in Model Parameters](<https://devfeed.tech/articles/some-memories-must-fade-persistence-and-decay-of-user-memories-in-model-parameters-145026.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25235>)

Author: Sanidhya Vijayvargiya, Rahul Lokesh

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: [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [lora](<https://devfeed.tech/topics/lora.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>)

Tags: [adapter](<https://devfeed.tech/tags/adapter.md>), [behavioral-shifts](<https://devfeed.tech/tags/behavioral-shifts.md>), [capacity](<https://devfeed.tech/tags/capacity.md>), [cl](<https://devfeed.tech/tags/cl.md>), [continual-learning](<https://devfeed.tech/tags/continual-learning.md>), [controller](<https://devfeed.tech/tags/controller.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [horizon](<https://devfeed.tech/tags/horizon.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [lifecycle](<https://devfeed.tech/tags/lifecycle.md>), [lora](<https://devfeed.tech/tags/lora.md>), [manage](<https://devfeed.tech/tags/manage.md>), [management](<https://devfeed.tech/tags/management.md>), [memory](<https://devfeed.tech/tags/memory.md>), [memory-management](<https://devfeed.tech/tags/memory-management.md>), [model-weights](<https://devfeed.tech/tags/model-weights.md>), [persistence](<https://devfeed.tech/tags/persistence.md>), [user](<https://devfeed.tech/tags/user.md>)

### AI overview

The paper proposes managing user memories directly in model weights, with a fixed-capacity LoRA adapter for storing facts and a learned lightweight controller for deciding what to retain, update, reinforce, or let fade. The adapter uses k-hot rank combinations intended to reduce catastrophic interference and supports independently controlled temporal decay. Evaluation on controlled long-horizon user trajectories tests recall while facts remain valid and abstention after they expire. The learned policy reaches 86% of oracle performance by balancing recall and abstention; the authors report that continual-learning and retrieval-augmented-generation baselines tend to default mainly to one behavior. These findings are from the described dataset and evaluation.

### Source excerpt

arXiv:2611.25235v1 Announce Type: new Abstract: Parametric memory allows Large Language Models to internalize knowledge directly into their weights, offering a potentially powerful alternative to retrieval-based memory (RAG). However, existing approaches to parametric memory are difficult to deploy as they largely mirror the Continual Learning (CL) objective of retaining information indefinitely. This is neither sustainable nor sufficient for a memory system, which must govern knowledge across its lifecycle by retaining stable facts, reinforcing recurring observations, updating changed beliefs, and allowing transient information to fade. We propose a system for parametric memory management consisting of a memory substrate (handling information storage and forgetting) and a learned policy (what to remember, how deeply, and for how long). Our substrate is a fixed-capacity LoRA adapter that consists of k-hot rank combinations which store facts without catastrophic interference and maintain an independently controlled temporal decay, enabling outdated information to fade while long-term facts persist. On this substrate, we train a lightweight controller that governs each incoming user event to ensure the memory system reflects the user's true, updated belief state. To evaluate how memory systems manage user memory, we introduce a controlled dataset of long-horizon user trajectories with varying persistence of facts based on changing belief states and user-behavioral shifts, and probe queries that test recall while information is valid and abstention after it expires. Our policy learns to effectively manage user memory over its entire lifecycle, balancing recall and abstention to achieve 86% of oracle performance, unlike CL and RAG baselines that primarily default to one of the two behaviors. By providing the first system to manage memory directly in model weights, this work establishes a foundation for long-horizon parametric memory.

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

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

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

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

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

Content type: article

Language: en

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

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

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

### AI overview

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

### Source excerpt

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

## Context as a Resource

DevFeed: [Context as a Resource](<https://devfeed.tech/articles/context-as-a-resource-145662.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26346>)

Author: Xufei Tian, Han Hu, Wenli Du

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

Content type: article

Language: en

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

Topics: [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [scheduling](<https://devfeed.tech/topics/scheduling.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [blocks](<https://devfeed.tech/tags/blocks.md>), [bus](<https://devfeed.tech/tags/bus.md>), [cells](<https://devfeed.tech/tags/cells.md>), [completion](<https://devfeed.tech/tags/completion.md>), [concurrent](<https://devfeed.tech/tags/concurrent.md>), [constraint](<https://devfeed.tech/tags/constraint.md>), [context](<https://devfeed.tech/tags/context.md>), [continuous](<https://devfeed.tech/tags/continuous.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [events](<https://devfeed.tech/tags/events.md>), [gate](<https://devfeed.tech/tags/gate.md>), [generative](<https://devfeed.tech/tags/generative.md>), [handoffs](<https://devfeed.tech/tags/handoffs.md>), [interface](<https://devfeed.tech/tags/interface.md>), [linear](<https://devfeed.tech/tags/linear.md>), [resource](<https://devfeed.tech/tags/resource.md>)

### AI overview

ClonAct proposes routerless management of concurrent agent contexts, using a non-generative Context MMU, in-place Context Cells, a footprint-aware Synaptic Bus with an isolated trial merge gate, and a wave-flushed Shared Trunk. The abstract reports that the merge gate raises true-conflict repository merge success from a 33.3% three-run mean to 63.3%; ClonAct reaches that rate with 45.9% fewer prompt tokens and avoids router collapse on compact models. Across three multi-stream benchmarks and three model families, it also matches the best reported completion rate under continuous surges (95.0%), with the lowest median wait and no timed-out status checks. These are abstract-level claims; the supplied text gives no further benchmark methodology or results.

### Source excerpt

arXiv:2611.26346v1 Announce Type: new Abstract: Managing concurrent tasks across separate agent sessions quickly exhausts human attention, motivating always-on personal agents behind a single continuous interface. Yet when every context shares identical frozen backbone weights, funneling interleaved dialogues and external events into one linear session induces cross-topic constraint bleed and head-of-line stalling. Conversely, router-ticket hierarchies incur lossy prose handoffs, heavy routing overhead, and blind merges - collapsing true-conflict repository merges to a 33.3% three-run mean despite high isolated branch passes. Rather than scheduling anthropomorphic roles, we introduce ClonAct, a routerless architecture that virtualizes context blocks directly through a pluggable single-pass non-generative Context MMU, in-place Context Cells, a footprint-aware Synaptic Bus with an isolated trial merge gate, and a wave-flushed Shared Trunk. Across three programmatic multi-stream benchmarks and three model families, our portable trial merge gate lifts true-conflict merges to 63.3%, while ClonAct's routerless virtualization attains this ceiling with 45.9% fewer prompt tokens and prevents compact-model router collapse. Under continuous surge streams, ClonAct matches top completion (95.0%) with the lowest median wait and zero timed-out status checks.

## FrontierReplay: Split-Free Exact Prefix Caching for Hybrid Language Models

DevFeed: [FrontierReplay: Split-Free Exact Prefix Caching for Hybrid Language Models](<https://devfeed.tech/articles/frontierreplay-split-free-exact-prefix-caching-for-hybrid-language-models-145128.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26020>)

Author: Zekun Wang, Yizhuo Wang

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

Content type: article

Language: en

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

Topics: [Cache](<https://devfeed.tech/topics/cache.md>), [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [approximation](<https://devfeed.tech/tags/approximation.md>), [architectures](<https://devfeed.tech/tags/architectures.md>), [attention](<https://devfeed.tech/tags/attention.md>), [branch](<https://devfeed.tech/tags/branch.md>), [caching](<https://devfeed.tech/tags/caching.md>), [capacity](<https://devfeed.tech/tags/capacity.md>), [chat](<https://devfeed.tech/tags/chat.md>), [checkpoint](<https://devfeed.tech/tags/checkpoint.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [kv-cache](<https://devfeed.tech/tags/kv-cache.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [layer](<https://devfeed.tech/tags/layer.md>), [layers](<https://devfeed.tech/tags/layers.md>), [load](<https://devfeed.tech/tags/load.md>), [prefill](<https://devfeed.tech/tags/prefill.md>), [prefix-caching](<https://devfeed.tech/tags/prefix-caching.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [question](<https://devfeed.tech/tags/question.md>)

### AI overview

FrontierReplay targets exact prefix caching in hybrid language models, where recurrent state updates limit reuse to saved positions. It identifies predictable structural boundaries, such as turn ends and known branch points, and creates exact checkpoints there without interrupting prefill: it logs a short window of recurrent-layer inputs and uses a cross-layer state-only replay kernel, reported to cost 6-37x less per token than full recomputation without host synchronization. Its retention policy prioritizes active anchors and proven branches and lends unused checkpoint slots to the attention KV cache. Across the evaluated architectures, scales, and workloads, the abstract reports 16-89% lower median time to first token, up to 1.73x higher capacity at an 80% SLO, and up to 4.26x higher goodput (3.67x at larger scales) versus existing exact caches. Versus approximate replay, it reports up to 1.54x higher goodput while preserving exact task accuracy; approximation suffered up to a 17% accuracy drop on long contexts.

### Source excerpt

arXiv:2611.26020v1 Announce Type: new Abstract: Hybrid language models combine self-attention with recurrent layers whose in-place state updates restrict prefix reuse to exact saved positions. Saving states on a coarse grid wastes reusable prefixes, whereas existing fine-grained exact caches must cut the prefill forward pass at each mid-prompt checkpoint, adding scheduler steps that outweigh the reuse gains under load. We observe that across multi-turn chat, agent loops, document question answering, and tree search, prefix reuse almost always ends at structural boundaries predictable in advance, such as turn ends and known branch points. We present FrontierReplay, a prefix caching system that materializes exact checkpoints at these boundaries without cutting the prefill. While the forward pass runs uncut, FrontierReplay logs a short window of recurrent-layer inputs and invokes a cross-layer, state-only replay kernel to build the target state 6-37x cheaper per token than full recomputation without host synchronization. A frontier-aware retention policy prioritizes active anchors and proven branches while lending dead checkpoint slots to the attention KV cache. Across diverse hybrid architectures, model scales, and workloads, FrontierReplay delivers clear gains over existing exact caches, lowering median time to first token (TTFT) by 16-89% (up to 8.9x), raising 80% service-level objective (SLO) capacity by up to 1.73x, and improving goodput by up to 4.26x (3.67x at larger scales). Compared with approximate replay methods, FrontierReplay delivers up to 1.54x higher goodput while preserving exact task accuracy, avoiding the up to 17% accuracy drop suffered by approximation on long contexts.

## Aggron: Aggressive Compression of Agentic KV Caches during Head-of-Line Stalls in the Request Queue

DevFeed: [Aggron: Aggressive Compression of Agentic KV Caches during Head-of-Line Stalls in the Request Queue](<https://devfeed.tech/articles/aggron-aggressive-compression-of-agentic-kv-caches-during-head-of-line-stalls-in-the-request-queue-146134.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26435>)

Author: Rishabh Ravi, Tony Hong, Chen Wang, Yue Zhu, Mengmei Ye, Hubertus Franke, Fan Lai, Josep Torrellas

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

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>)

Topics: [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Compression](<https://devfeed.tech/topics/compression.md>), [queueing theory](<https://devfeed.tech/topics/queueing-theory.md>), [performance-engineering](<https://devfeed.tech/topics/performance-engineering.md>), [vllm](<https://devfeed.tech/topics/vllm.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [cache](<https://devfeed.tech/tags/cache.md>), [capacity](<https://devfeed.tech/tags/capacity.md>), [compression](<https://devfeed.tech/tags/compression.md>), [context-compression](<https://devfeed.tech/tags/context-compression.md>), [cs-ar](<https://devfeed.tech/tags/cs-ar.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [engine](<https://devfeed.tech/tags/engine.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [kv-cache](<https://devfeed.tech/tags/kv-cache.md>), [latency](<https://devfeed.tech/tags/latency.md>), [llm](<https://devfeed.tech/tags/llm.md>), [load](<https://devfeed.tech/tags/load.md>), [memory](<https://devfeed.tech/tags/memory.md>), [model](<https://devfeed.tech/tags/model.md>), [queue](<https://devfeed.tech/tags/queue.md>), [request](<https://devfeed.tech/tags/request.md>), [serving](<https://devfeed.tech/tags/serving.md>), [stalled](<https://devfeed.tech/tags/stalled.md>), [throughput](<https://devfeed.tech/tags/throughput.md>)

### AI overview

Aggron addresses KV-cache limits in long-running LLM agents by summarizing selected cache content at every turn, keeping each summarization request lightweight. It runs these requests in a separate queue while the corresponding agent request is stalled behind a head-of-line block, using capacity left idle in the main queue; it launches summarization only when it predicts completion before that agent request executes. The abstract says this approach retains accuracy and, versus state-of-the-art asynchronous summarization at high load, reduces P99 program latency by 27-31% and increases throughput by 1.34-1.40x. The supplied text is an abstract, so it does not provide evaluation details or broader comparisons.

### Source excerpt

arXiv:2611.26435v1 Announce Type: new Abstract: LLM agents run long, multi-turn programs whose contexts grow at every step, and serving them is limited by KV cache capacity. To alleviate this limitation, systems use context compression techniques, which typically wait until the KV cache crosses a large threshold and then summarize large spans of history at once, either in the background while the agent progresses or on the critical path. These summarizations can be done using the same model running on the same engine, or using the same or a different model running on extra hardware. When running on the same engine, summarization competes with the requests being served for both compute and memory capacity. To maximize the cost-effectiveness of summarization, this paper presents a new serving system called {\em Aggron}. Aggron summarizes agentic requests at every turn and selectively summarizes only certain parts of the KV cache. As a result, Aggron retains accuracy and keeps summarization requests lightweight. Moreover, Aggron launches summarization requests from a separate {\em Summarization Queue} while the corresponding agentic request whose KV cache we want to compress is stalled in the main request queue due to head-of-line stalls. The Summarization queue utilizes compute and memory capacity left over by the head-of-line stalls in the main queue. Further, to maximize efficiency, the server issues summarizations only when it predicts that they can complete before the corresponding agentic request will finally execute. In our evaluation, we compare Aggron to state-of-the-art asynchronous summarization. At high load, Aggron reduces P99 program latency by $27$--$31\%$, and raises throughput by $1.34$--$1.40\times$.

## Spring AI 2.1.0 GA and 2.0.3 GA Available Now

DevFeed: [Spring AI 2.1.0 GA and 2.0.3 GA Available Now](<https://devfeed.tech/articles/spring-ai-2-1-0-ga-and-2-0-3-ga-available-now-146701.md>)

Original publisher: [Read original article](<https://spring.io/blog/2026/11/20/spring-ai-2-1-0-GA-available-now>)

Author: tzolov

Published: 2026-11-20T00:00:00Z

Content type: release

Language: en

Sources: [Spring](<https://devfeed.tech/sources/spring.md>)

Topics: [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Multi-step AI processes](<https://devfeed.tech/topics/multi-step-ai-processes.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [api](<https://devfeed.tech/tags/api.md>), [batch](<https://devfeed.tech/tags/batch.md>), [boot](<https://devfeed.tech/tags/boot.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [decision](<https://devfeed.tech/tags/decision.md>), [decision-models](<https://devfeed.tech/tags/decision-models.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [event-driven](<https://devfeed.tech/tags/event-driven.md>), [guardrail](<https://devfeed.tech/tags/guardrail.md>), [harness](<https://devfeed.tech/tags/harness.md>), [java](<https://devfeed.tech/tags/java.md>), [maven](<https://devfeed.tech/tags/maven.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [memory](<https://devfeed.tech/tags/memory.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [model-context-protocol](<https://devfeed.tech/tags/model-context-protocol.md>), [openai](<https://devfeed.tech/tags/openai.md>), [parts](<https://devfeed.tech/tags/parts.md>), [reactive](<https://devfeed.tech/tags/reactive.md>), [recall](<https://devfeed.tech/tags/recall.md>), [release](<https://devfeed.tech/tags/release.md>), [responses-api](<https://devfeed.tech/tags/responses-api.md>), [security](<https://devfeed.tech/tags/security.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [session](<https://devfeed.tech/tags/session.md>), [spring](<https://devfeed.tech/tags/spring.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [web-applications](<https://devfeed.tech/tags/web-applications.md>)

### AI overview

Spring AI 2.1.0 GA, built on Spring Boot 4.2, adds a stateless MCP 2026-07-28 protocol, typed Decision Models, ordered message parts that preserve reasoning and provider-specific payloads, and an OpenAI Responses API chat model. Its agent building blocks include a Session API with compaction and event recall (ChatMemory is deprecated for removal in 3.0), per-tool approval pauses, configurable per-turn call limits, and marked guardrail refusals. Eleven vector stores can now write and search vectors computed elsewhere, with width checks and stable-ID replacement. The release also includes reference-documentation changes and security fixes; Spring AI 2.0.3 carries the fixes on the 2.0.x line. Upgrading to 2.1 generally involves updating Spring AI and Spring Boot together, but some security fixes change behavior, and applications upgrading from 2.0.2 or earlier are directed to review the 2.0.2 and 2.0.3 notes.

### Source excerpt

On behalf of the Spring AI team and everyone who has contributed, I'm happy to announce that Spring AI 2.1.0 has been released and is now available from Maven Central! Release notes | Upgrade notes | Reference documentation Spring AI 2.1 arrives five months after 2.0.0 GA. It is built on Spring Boot 4.2 and contains more than 430 commits from 86 contributors. This post covers everything that changed since 2.0.0: the features of the 2.1 milestones and release candidates, what was added after RC2, and the additions that already shipped in 2.0.1 and 2.0.2. The short version: MCP 2026-07-28. Servers and clients for the new, stateless revision of the Model Context Protocol, next to the existing ones. Decision Models. A new model API for typed yes/no, choice and score decisions, with three providers. A richer message model. Messages hold ordered parts, so reasoning, tool calls and provider-specific blocks survive a round trip. The OpenAI Responses API is supported next to Chat Completions. The building blocks of an agent harness. The Session API, with session memory, compaction and recall, replaces ChatMemory. Tool calls can wait for a person's approval and are limited per turn, and guardrail refusals are marked as such. Your own embeddings. Eleven vector stores can write and search with vectors you computed yourself. New reference documentation, organized around tasks, with a quickstart and tutorials. Security. Fixes for 13 CVEs, which Spring AI 2.0.3 has as well. Next: Spring AI Agent. A new project for composing and orchestrating agents, built on Spring AI 2.1, starts incubating in early December. See What's next. The following map shows the building blocks of Spring AI 2.1, with the community projects in blue. It comes from the new reference documentation, where the blocks link to their pages. MCP 2026-07-28 The 2026-07-28 revision is a redesign of the Model Context Protocol. It is stateless: there is no initialize handshake and no session, every request carries the p

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

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

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

Author: Richa Sethi; Patrick Chan

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

Content type: news

Language: en

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

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

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

### AI overview

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

### Source excerpt

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

## Your AI Agent Is Only Seeing Half The Answer

DevFeed: [Your AI Agent Is Only Seeing Half The Answer](<https://devfeed.tech/articles/your-ai-agent-is-only-seeing-half-the-answer-145830.md>)

Original publisher: [Read original article](<https://www.starburst.io/blog/your-ai-agent-is-only-seeing-half-the-answer>)

Published: 2026-11-19T18:00:05Z

Content type: article

Language: en

Sources: [Starburst Data](<https://devfeed.tech/sources/starburst-data.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Apache Iceberg](<https://devfeed.tech/topics/apache-iceberg.md>)

Tags: [access-control](<https://devfeed.tech/tags/access-control.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-data](<https://devfeed.tech/tags/ai-data.md>), [ai-data-engine](<https://devfeed.tech/tags/ai-data-engine.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [api](<https://devfeed.tech/tags/api.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [auditing](<https://devfeed.tech/tags/auditing.md>), [business](<https://devfeed.tech/tags/business.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [connectors](<https://devfeed.tech/tags/connectors.md>), [console](<https://devfeed.tech/tags/console.md>), [content](<https://devfeed.tech/tags/content.md>), [context](<https://devfeed.tech/tags/context.md>), [contracts](<https://devfeed.tech/tags/contracts.md>), [control](<https://devfeed.tech/tags/control.md>)

### AI overview

Starburst AIDA and NetApp AIDE are presented as a way to answer questions that require both database values and document context, such as matching contract renewal dates and spend with notice clauses. AIDA plans the question, sends structured queries through Starburst's federated SQL engine and document searches through AIDE's MCP server, then joins the results and cites source versions. Starburst is described as querying structured and semi-structured data in place across 50+ connectors, with row- and column-level controls, masking, and auditing. AIDE makes files on NetApp storage searchable, preserves file permissions, and exposes content through MCP; its Metadata Services catalog reads metadata without copying files or using GPUs. The stated tradeoff is that this approach avoids a separate external index, but its document capabilities depend on files being accessible through AIDE and NetApp storage interfaces. The excerpt recommends starting with one cross-source question and a joint architecture workshop.

### Source excerpt

Most teams building AI agents hit the same problem. Everything isn't in the same place. ...

## MEM-STRESS: Longitudinal Field Study of a Wearable-Informed AI Chatbot for Stress Management

DevFeed: [MEM-STRESS: Longitudinal Field Study of a Wearable-Informed AI Chatbot for Stress Management](<https://devfeed.tech/articles/mem-stress-longitudinal-field-study-of-a-wearable-informed-ai-chatbot-for-stress-management-142691.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23691>)

Author: Soorya Ram Shimgekar, Pragya Singh, Shivam Sharma, Chandrayee Roy, Koustuv Saha, Antti Oulasvirta, Talayeh Aledavood

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

Content type: news

Language: en

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

Topics: [human computer interaction](<https://devfeed.tech/topics/human-computer-interaction.md>), [Chat Bot](<https://devfeed.tech/topics/chatbot.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-chatbot](<https://devfeed.tech/tags/ai-chatbot.md>), [chatbot](<https://devfeed.tech/tags/chatbot.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-hc](<https://devfeed.tech/tags/cs-hc.md>), [field](<https://devfeed.tech/tags/field.md>), [management](<https://devfeed.tech/tags/management.md>), [stress](<https://devfeed.tech/tags/stress.md>), [study](<https://devfeed.tech/tags/study.md>), [wearable](<https://devfeed.tech/tags/wearable.md>)

### AI overview

MEM-STRESS uses wearable ring data as layered memory--daily records, deviations from baseline, and LLM-generated summaries--to ground multi-session stress-support conversations in Dialectical Behavior Therapy. In a four-week, non-randomized study of 60 adults, it was compared with a chatbot that remembered only past conversations. MEM-STRESS referenced physiological features in 71.8% of sessions and suggested body-related skills more often (14.5% vs. 5.7%). Participants praised personalization more often (44.4% vs. 14.3%); perceived stress fell 14.2% from baseline, compared with 3.6% in Control, but the group difference was not significant. The findings suggest feasibility and potential personalization benefits; larger randomized studies are needed.

### Source excerpt

arXiv:2611.23691v1 Announce Type: cross Abstract: Stress is an increasingly prevalent concern, creating a need for accessible and personalized support. Stress-management chatbots primarily rely on what users report, which may not capture their physiological changes. Wearables capture these changes, but chatbots rarely use them as memory across conversations. We therefore present MEM-STRESS, a stress-support chatbot that turns a wearable ring's physiological data into a layered memory of daily records, baseline deviations, LLM-generated summaries, and uses it to drive multi-session conversations grounded in Dialectical Behavior Therapy (DBT). In a four-week, non-randomized study with 60 adults, we compared MEM-STRESS (Treatment) with a chatbot remembering only past conversations (Control). Memory shaped the conversations: The Treatment chatbot referenced participants' physiological features (e.g., activity in 71.8% of sessions) and suggested more body-related DBT skills than Control (14.5% vs. 5.7%), with Treatment participants also using slightly more body-related words (1.76% vs. 1.45%). Treatment participants praised personalization three times as often (44.4% vs. 14.3%), more frequently reported reflecting differently on stress (69.0% vs. 46.4%, not significant), and described gaining insight into their stress signals. Their perceived stress fell 14.2% from baseline versus 3.6% for Control, though the group difference was not significant. Grounding stress-support chatbots in layered physiological memory is thus feasible and may improve perceived personalization, motivating larger randomized studies.

## Resolution as Attention for Efficient Agent Memory Perception

DevFeed: [Resolution as Attention for Efficient Agent Memory Perception](<https://devfeed.tech/articles/resolution-as-attention-for-efficient-agent-memory-perception-142794.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24422>)

Author: Siqi Xiang, Zhipeng Xu, Shengrui Liu, Zulong Chen, Chunyan Miao, Shijian Lu

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 Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-memory](<https://devfeed.tech/tags/agent-memory.md>), [agents](<https://devfeed.tech/tags/agents.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [attention](<https://devfeed.tech/tags/attention.md>), [computer-science](<https://devfeed.tech/tags/computer-science.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [layer](<https://devfeed.tech/tags/layer.md>), [llm](<https://devfeed.tech/tags/llm.md>), [management](<https://devfeed.tech/tags/management.md>), [mechanism](<https://devfeed.tech/tags/mechanism.md>), [memory](<https://devfeed.tech/tags/memory.md>), [memory-management](<https://devfeed.tech/tags/memory-management.md>), [multiple](<https://devfeed.tech/tags/multiple.md>), [performance](<https://devfeed.tech/tags/performance.md>), [relevance](<https://devfeed.tech/tags/relevance.md>), [tasks](<https://devfeed.tech/tags/tasks.md>), [token](<https://devfeed.tech/tags/token.md>), [token-consumption](<https://devfeed.tech/tags/token-consumption.md>), [token-savings](<https://devfeed.tech/tags/token-savings.md>)

### AI overview

Resolution as Attention (RAA) allocates perceptual detail across an agent's interaction history by rendering past interactions as images and adjusting each image's resolution according to its relevance to the next decision. A lightweight relevance estimator is trained with teacher guidance and optimized to preserve decision consistency while reducing visual-token use. The abstract reports over 50% lower token consumption without compromising task performance across multiple tasks and backbones. RAA can also be added as a perception layer to existing memory-management methods for further token savings. These claims are based on the supplied abstract; it gives no task-level results or implementation details.

### Source excerpt

arXiv:2611.24422v1 Announce Type: new Abstract: LLM-based agents accumulate extensive interaction histories when solving complex, long-horizon tasks, making efficient memory management critical to their performance and scalability. While existing memory management methods primarily focus on what to retain or retrieve, they often overlook how much perceptual detail should be allocated to individual past interactions. We posit that effective agent memory depends not only on the information preserved, but also on the granularity at which each past interaction is perceived. Motivated by this insight, we propose Resolution as Attention (RAA), a memory perception mechanism that uses visual resolution as a means of attention allocation across interaction histories. RAA renders past interactions as images and dynamically adjusts their resolution at every step according to their relevance to the agent's upcoming decision, preserving fine-grained information for critical interactions while reducing visual-token consumption for less relevant ones. To adaptively determine the perceptual fidelity of each interaction, we train a lightweight relevance estimator with teacher-model guidance and further optimize it to preserve the agent's decision consistency at a reduced visual-token cost. Experiments across multiple tasks and backbones show that RAA reduces token consumption by over 50% without compromising task performance. Moreover, RAA can be integrated as a plug-in perception layer with existing memory management methods, yielding further token savings and revealing adaptive perception as a complementary dimension of agent memory.

## MoE-Context: Show the Model Only What It Needs

DevFeed: [MoE-Context: Show the Model Only What It Needs](<https://devfeed.tech/articles/moe-context-show-the-model-only-what-it-needs-142788.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24379>)

Author: Vedant Navale

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

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: [AI Context Management](<https://devfeed.tech/topics/ai-context-management.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>), [block](<https://devfeed.tech/tags/block.md>), [blocks](<https://devfeed.tech/tags/blocks.md>), [cache](<https://devfeed.tech/tags/cache.md>), [context](<https://devfeed.tech/tags/context.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [failed](<https://devfeed.tech/tags/failed.md>), [key-value-cache](<https://devfeed.tech/tags/key-value-cache.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [linear](<https://devfeed.tech/tags/linear.md>), [lookup](<https://devfeed.tech/tags/lookup.md>), [model](<https://devfeed.tech/tags/model.md>), [moe](<https://devfeed.tech/tags/moe.md>), [patterns](<https://devfeed.tech/tags/patterns.md>), [qwen3](<https://devfeed.tech/tags/qwen3.md>), [recall](<https://devfeed.tech/tags/recall.md>), [subagents](<https://devfeed.tech/tags/subagents.md>), [switching](<https://devfeed.tech/tags/switching.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>)

### AI overview

MoE-Context keeps context in blocks and, at each step, selects needed blocks while retaining one-line notes for the rest; hidden blocks are masked in a shared key-value cache rather than deleted. In a laptop experiment with Qwen3-1.7B on a synthetic lookup task, showing only the needed block raised accuracy from 93 to 119 out of 120. The model's own selection was weaker: a supervised linear probe improved selection accuracy from 80 to 110 out of 120, while keyword search was perfect on this task. The probe did not transfer to a second task. The authors also describe undoing failed attempts and running subagents without creating a new context as uses enabled by switching blocks.

### Source excerpt

arXiv:2611.24379v1 Announce Type: new Abstract: AI agents read their whole history at every step. People do not work like that: we keep what the moment needs and hold the rest as a rough note we can recall. MoE-Context applies this to language models. The context is split into blocks. Before each step a fast yes or no pass decides which blocks the step needs; the rest stay as one-line notes that can be brought back, and nothing is deleted. In the version we build, one model makes this decision and then answers, over a single key-value cache where hidden blocks are masked rather than removed. On a laptop with Qwen3-1.7B and a synthetic lookup task, showing only the needed block raises accuracy from 93 to 119 of 120, and a masked block is as hidden as a deleted one. The model's own picking is the weak part. A supervised linear probe written into spare output rows lifts its accuracy from 80 to 110 of 120, but simple keyword search picks perfectly on this task, and the probe does not transfer to a second task. We report these results openly, along with two cheap usage patterns that block switching enables: undoing a failed attempt and running subagents without a new context.

## MemoSync: Co-Managing Developer-Agent Metamemory Across Contexts

DevFeed: [MemoSync: Co-Managing Developer-Agent Metamemory Across Contexts](<https://devfeed.tech/articles/memosync-co-managing-developer-agent-metamemory-across-contexts-142206.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24165>)

Author: Baiqiao Zhang, Junze Li, Chunyang Luo, Yuying Tang, Wenshuo Zhang, Shiyuan Piao, Dingdong Liu, Shuai Ma, Xiaojuan Ma

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

Content type: article

Language: en

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

Topics: [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>)

Tags: [agent-memory](<https://devfeed.tech/tags/agent-memory.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [control](<https://devfeed.tech/tags/control.md>), [cs-hc](<https://devfeed.tech/tags/cs-hc.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [developer](<https://devfeed.tech/tags/developer.md>), [human-computer-interaction](<https://devfeed.tech/tags/human-computer-interaction.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>)

### AI overview

MemoSync makes coding-agent memory a shared representation: the agent proposes memory candidates and reports which items it uses, while developers can review, edit, and scope them. A formative study with 12 developers informed four dimensions of memory monitoring and control. In a comparison with two baselines (N=132), MemoSync participants had significantly higher task performance and the highest mean developer-agent memory alignment; exploratory analysis attributed the alignment advantage mainly to better monitoring accuracy. Participants took substantially more monitoring and control actions without reporting increased workload. A week-long deployment with nine developers found these practices fit into everyday development work.

### Source excerpt

arXiv:2611.24165v1 Announce Type: cross Abstract: AI coding agents increasingly manage what context carries across sessions and projects, but developers have limited visibility into what these agents store, retrieve, and apply. This opacity creates a metamemory problem: the developer's meta-level judgments about what should be remembered are separated from the agent's object-level memory operations, disrupting the monitoring and control that keep the two levels aligned. We conducted a formative study with 12 developers and identified what they want to monitor and control across four dimensions of agent memory use. Based on these findings, we designed MemoSync, a co-management system that treats agent memory as a shared, operable representation: the agent proposes memory candidates and reports which items it uses, and the developer reviews, edits, and scopes them. In a between-subjects study (N=132) against two baselines, MemoSync participants achieved significantly higher task performance and the highest mean developer-agent memory alignment. In an exploratory mediation analysis, the alignment advantage was primarily driven by improved monitoring accuracy. Despite performing substantially more monitoring and control actions, participants reported no increase in perceived workload. A week-long deployment with nine developers showed that memory monitoring and control fit into everyday development work. MemoSync is open-sourced at https://github.com/SLEEPYBQ/MemoSync.

## HorizonBench: Long-Horizon Personalization with Evolving Preferences

DevFeed: [HorizonBench: Long-Horizon Personalization with Evolving Preferences](<https://devfeed.tech/articles/horizonbench-long-horizon-personalization-with-evolving-preferences-142518.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2604.17283>)

Author: Shuyue Stella Li, Bhargavi Paranjape, Kerem Oktar, Zhongyao Ma, Gelin Zhou, Lin Guan, Na Zhang, Sem Park, Lin Chen, Diyi Yang, Yulia Tsvetkov, Asli Celikyilmaz

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 Chat](<https://devfeed.tech/topics/ai-chat.md>), [personalization](<https://devfeed.tech/topics/personalization.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>)

Tags: [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [frontier](<https://devfeed.tech/tags/frontier.md>), [generator](<https://devfeed.tech/tags/generator.md>), [history](<https://devfeed.tech/tags/history.md>), [memory](<https://devfeed.tech/tags/memory.md>), [personalization](<https://devfeed.tech/tags/personalization.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>)

### AI overview

HorizonBench tests whether assistants can update their model of a user when preferences change implicitly after life events. Its generator creates six months of conversation, calibrated using 83,024 ratings from 160 people over 13 weeks; the benchmark contains 4,245 questions from 360 users and includes outdated preferences as answer choices. Across 25 evaluated frontier models, outdated preferences were selected more often than evenly distributed errors would predict, and the best accuracy was 52.8%. For two recent models, restricting input to relevant conversations did not improve scores over full history, while explicitly stating the preference change raised accuracy by 11-22 points. Retrieval and memory methods did not recover that gain, suggesting that remembering prior statements and identifying current preferences are distinct capabilities.

### Source excerpt

arXiv:2604.17283v2 Announce Type: replace-cross Abstract: Personal assistants now talk with the same user for months, and users' preferences change as their lives change; an assistant that keeps serving a preference the user has outgrown fails that user. Real conversations do not record when or why a preference changed, and existing benchmarks either hold preferences fixed or have the user state the change, so they cannot tell whether a model forgot what the user said or failed to update its belief about the user. We introduce HorizonBench and its data generator, which samples how a user's preferences change and generates six months of conversation from that sequence; each change follows a life event that the user mentions without stating the new preference. A human longitudinal preference dataset that we collect and release, 83,024 ratings from 160 people over 13 weeks, sets how often and how much life events change preferences. HorizonBench contains 4,245 questions from 360 users, and when a preference has changed, its earlier value is one of the answer options. All 25 frontier models we evaluate choose the outdated preference more often than evenly spread errors would predict, and the best reaches 52.8% accuracy. Two of the newest models score no higher when given only the relevant conversations than with the full history, yet one added sentence stating the change raises their accuracy by 11 to 22 points, and retrieval and memory methods do not recover the lost accuracy. Remembering what a user said and knowing what the user prefers now are therefore separate capabilities, and HorizonBench, its generator, and the human dataset support research on both.

## F$^3$: What Makes Good Experience in World-Action Models?

DevFeed: [F$^3$: What Makes Good Experience in World-Action Models?](<https://devfeed.tech/articles/f-3-what-makes-good-experience-in-world-action-models-142824.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24708>)

Author: Zihe Huang, Sirui Zhou, Haozhi Han, Ruge Zhang, Teng Ma, Tao Ma, Zheng Liu, Ce Zhang, Ting Cao, Yunxin Liu, Yunquan Zhang, Yifeng Chen, Kun Li

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

Content type: article

Language: en

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

Topics: [World models](<https://devfeed.tech/topics/world-models.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Cosmos](<https://devfeed.tech/topics/cosmos.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [context](<https://devfeed.tech/tags/context.md>), [cosmos](<https://devfeed.tech/tags/cosmos.md>), [cosmos-3](<https://devfeed.tech/tags/cosmos-3.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [examples](<https://devfeed.tech/tags/examples.md>), [experience](<https://devfeed.tech/tags/experience.md>), [failed](<https://devfeed.tech/tags/failed.md>), [failures](<https://devfeed.tech/tags/failures.md>), [form](<https://devfeed.tech/tags/form.md>), [fusion](<https://devfeed.tech/tags/fusion.md>), [helps](<https://devfeed.tech/tags/helps.md>), [images](<https://devfeed.tech/tags/images.md>), [library](<https://devfeed.tech/tags/library.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [nano](<https://devfeed.tech/tags/nano.md>), [native](<https://devfeed.tech/tags/native.md>), [policy](<https://devfeed.tech/tags/policy.md>), [raises](<https://devfeed.tech/tags/raises.md>), [world](<https://devfeed.tech/tags/world.md>)

### AI overview

F$^3$ improves how world-action models use experience by deciding what to store, when to retrieve it, and how to feed it into the policy. Form turns successful and failed rollouts into short, verified operation records; Fit trains the policy to read records and predict when they will help; Fusion adds their images, text, and actions as a prefix and action prior. After training once on 200 examples, the model uses a growing experience library and reports state-of-the-art results on MolmoSpaces and RoboLab, without training on RoboLab. Compared with native Cosmos 3 Nano, it reports success gains of 12.0 and 10.8 percentage points, 12.2% and 11.3% fewer steps to success, and 57% fewer regressions. These figures are from the supplied abstract.

### Source excerpt

arXiv:2611.24708v1 Announce Type: new Abstract: Deployed world-action models (WAMs) can keep improving only if they make good use of their own experience. Existing methods supply retrieved rollouts or demonstrations to the policy as context, yet such experience often turns previously solved tasks into failures. What, then, makes good experience for a WAM? We show that experience is valuable only in use: its value depends not on whether the source rollout succeeded but on what is stored, when it is used, and where it enters the policy. We therefore propose F$^3$, which makes these three decisions with Form, Fit, and Fusion. Form compresses successful and failed rollouts alike into short, verified operation records; Fit teaches the policy to read a record and to predict when it helps; Fusion injects the record's images, text and actions into the policy as a prefix and an action prior. Trained once on only 200 examples and deployed with a growing experience library, the model achieves state-of-the-art results on MolmoSpaces and RoboLab without any training on RoboLab: over native Cosmos 3 Nano, it raises success by 12.0 pp and 10.8 pp, reduces steps to success by 12.2% and 11.3%, and cuts regressions by 57%.

## What Does a Harness Buy? Tokens, Mostly

DevFeed: [What Does a Harness Buy? Tokens, Mostly](<https://devfeed.tech/articles/what-does-a-harness-buy-tokens-mostly-142118.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.04433>)

Author: Yangze Liu, Zhongyi Han

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

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

Topics: [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [context](<https://devfeed.tech/tags/context.md>), [context-management](<https://devfeed.tech/tags/context-management.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [harness](<https://devfeed.tech/tags/harness.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [leaderboards](<https://devfeed.tech/tags/leaderboards.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [opencode](<https://devfeed.tech/tags/opencode.md>), [pass](<https://devfeed.tech/tags/pass.md>), [points](<https://devfeed.tech/tags/points.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [swe-bench](<https://devfeed.tech/tags/swe-bench.md>), [system](<https://devfeed.tech/tags/system.md>), [tokens](<https://devfeed.tech/tags/tokens.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

Across seven models tested with Claude Code, mini-SWE-agent, and OpenCode, no harness leads consistently. On SWE-bench Verified and two other benchmarks, bounded differences between harnesses are 2-5 points, and swapping harnesses changes about as many task outcomes as rerunning the same setup. Some model-harness pairings show larger, model-dependent effects: OpenCode trails by 8-9 points on one model and leads by 14 on another. Cost differences also vary by model, ranging from under 10% to 3-4 times. The authors conclude that harness comparisons should be reported alongside reruns; the abstract does not establish a universally better harness.

### Source excerpt

arXiv:2610.04433v2 Announce Type: replace-cross Abstract: A coding agent is a language model inside a harness: the system prompt, the tools, and the context management that let a chat model work in a repository. Most of the engineering on these agents goes into the harness, and vendors and leaderboards credit it with score gains. Earlier studies have fixed the model and swapped the harness, but have not measured whether the swap changes the pass rate more than running the same harness again. We run seven models through three production harnesses, Claude Code, mini-SWE-agent, and OpenCode, on SWE-bench Verified and two benchmarks of other kinds, and rerun them unchanged. No harness leads consistently across models. Where the data can bound the difference between two harnesses, the bound is 2 to 5 points, and a harness swap changes about as many task outcomes as a rerun. The exceptions are harness effects in particular pairings of model and harness, whose direction changes with the model: OpenCode trails by 8 to 9 points on one model and leads by 14 on another. Cost differences between harnesses also depend on the model, from under 10% to 3 to 4 times. Which harness is better therefore has no answer apart from the model, and a harness difference should be reported next to a rerun.

## ElephantAgent: Contextual State Continuity in Agentic Systems

DevFeed: [ElephantAgent: Contextual State Continuity in Agentic Systems](<https://devfeed.tech/articles/elephantagent-contextual-state-continuity-in-agentic-systems-142538.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2607.01919>)

Author: Jiankai Jin, Xiangzheng Zhang, Zhao Liu, Wenzhuo Xu, Dongdong Yang, Deyue Zhang, Quanchen Zou

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

Content type: article

Language: en

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

Topics: [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [DeepSeek Harness](<https://devfeed.tech/topics/dsh.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-systems](<https://devfeed.tech/tags/agentic-systems.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [attack](<https://devfeed.tech/tags/attack.md>), [context](<https://devfeed.tech/tags/context.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [deepseek-harness](<https://devfeed.tech/tags/deepseek-harness.md>), [digest](<https://devfeed.tech/tags/digest.md>), [execution](<https://devfeed.tech/tags/execution.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [memory](<https://devfeed.tech/tags/memory.md>), [out-of-band](<https://devfeed.tech/tags/out-of-band.md>), [overhead](<https://devfeed.tech/tags/overhead.md>), [planning](<https://devfeed.tech/tags/planning.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [prompt-injection](<https://devfeed.tech/tags/prompt-injection.md>), [protocol](<https://devfeed.tech/tags/protocol.md>), [rollback](<https://devfeed.tech/tags/rollback.md>), [security](<https://devfeed.tech/tags/security.md>), [state](<https://devfeed.tech/tags/state.md>), [system](<https://devfeed.tech/tags/system.md>)

### AI overview

ElephantAgent aims to prevent out-of-band tool and memory poisoning by checking whether a bounded, security-critical portion of an agent's context matches its latest authorized state. Before each planning and execution cycle, it recomputes a digest and verifies it against a linearizable ledger of state transitions maintained over replicated trusted hardware; historical traceability makes transitions attributable and recoverable. In tests, ElephantDSH, an integration with DeepSeek Harness, withstood the reported out-of-band attacks and recovered from in-band prompt injection in all trials. Of five evaluated defenses that check only incoming context, all leaked targeted content under rollback and three did so under rug-pull attacks. Normal coding tasks incurred 1.02-1.07x relative overhead over DSH, with model latency variation removed.

### Source excerpt

arXiv:2607.01919v2 Announce Type: replace Abstract: Agentic systems enhance their capabilities by invoking external tools and maintaining persistent memory. However, recent tool and memory poisoning attacks can covertly bias agent behavior. We observe that such attacks mounted out of band share a single enabler: each succeeds only by presenting the agent with a contextual state (e.g., tool state and memory) that is not the latest faithfully evolved one. This observation suggests that a continuity check over the contextual state covers this family of attacks. We present ElephantAgent, a protocol that enforces Contextual State Continuity over the bounded, security-critical subset of the agent's context. Before each planning-and-execution cycle, ElephantAgent recomputes the digest of the local contextual state and verifies it against the latest authorized digest in a linearizable ledger of state transitions, maintained over replicated trusted hardware. The protocol also provides Historical Traceability, a secondary guarantee that keeps state transitions attributable and recoverable. We integrate ElephantAgent into DeepSeek Harness (DSH) and implement ElephantDSH, an agentic system protected by contextual state verification. ElephantDSH withstood all out-of-band attack attempts, from rug pulls and rollbacks to attacks on its own mechanism, and recovered from an in-band prompt injection in all trials. By comparison, existing defenses typically check only what enters the context: of the five we evaluated, all leaked the targeted content under the rollback, and three also under the rug pull. ElephantDSH completed all normal coding tasks with a relative overhead of 1.02-1.07$\times$ over the original DSH with model latency variation removed.

## Semantic Context Handoff with On-Demand Evidence for Long-Horizon Agents

DevFeed: [Semantic Context Handoff with On-Demand Evidence for Long-Horizon Agents](<https://devfeed.tech/articles/semantic-context-handoff-with-on-demand-evidence-for-long-horizon-agents-142784.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24357>)

Author: Guolong Zheng, Chen Hou, Xu Yang, Jianshan Zhang, Tao Huang

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

Content type: article

Language: en

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

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

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [context](<https://devfeed.tech/tags/context.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [execution](<https://devfeed.tech/tags/execution.md>), [horizon](<https://devfeed.tech/tags/horizon.md>), [inference](<https://devfeed.tech/tags/inference.md>), [interaction](<https://devfeed.tech/tags/interaction.md>), [llm](<https://devfeed.tech/tags/llm.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [pass](<https://devfeed.tech/tags/pass.md>), [performance](<https://devfeed.tech/tags/performance.md>), [prompting](<https://devfeed.tech/tags/prompting.md>), [recovery](<https://devfeed.tech/tags/recovery.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [swe-bench](<https://devfeed.tech/tags/swe-bench.md>), [system](<https://devfeed.tech/tags/system.md>), [tokens](<https://devfeed.tech/tags/tokens.md>)

### AI overview

Semantic Context Handoff (SCH) separates an agent's compact interpretation of its current state from the action-observation evidence supporting it. Earlier evidence remains addressable and can re-enter context when relevant, without separate summarization or retrieval-model calls. In a controlled 150-task SWE-bench study, evidence recovery raised Pass@1 from 80.0% to 86.9% with essentially unchanged token use and execution time. In a complete-system comparison, SCH reached 86.9% Pass@1 using 43% fewer tokens and 41% less wall-clock time than the strongest baseline by task performance. Across evaluated models and benchmarks, it reduced token use versus full-history prompting while remaining competitive with or improving on the other evaluated baselines. Trajectory analysis found recovery of evidence from much earlier interactions, beyond a recent-context window.

### Source excerpt

arXiv:2611.24357v1 Announce Type: new Abstract: Traditional long-horizon LLM agents often hand off context through full-history prompting, retaining all previous action--observation interactions. As execution proceeds, this history keeps growing, increasing inference cost and potentially degrading accuracy. Existing methods control this growth by preserving compact conclusions while removing earlier observations, but doing so can discard evidence that later becomes relevant. We introduce Semantic Context Handoff (SCH), whose central abstraction is state--evidence separation: a compact semantic state carries the agent's current interpretation, while supporting action--observation evidence remains separately addressable and can re-enter context when later execution makes it relevant, without separate summarization or retrieval-model calls. Empirically, SCH improves long-horizon agent performance while substantially reducing context cost. In a controlled 150-task SWE-bench study, SCH's evidence recovery improves Pass@1 from $80.0\%$ to $86.9\%$ at essentially unchanged token use and execution time. In the complete-system comparison, SCH achieves 86.9% Pass@1 while using 43% fewer tokens and 41% less wall-clock time than the strongest baseline by task performance. Across models and benchmarks, SCH consistently reduces token use relative to full-history prompting while remaining competitive with or improving upon the evaluated baselines. Trajectory analysis confirms that SCH recovers evidence from substantially earlier parts of the interaction history rather than merely preserving a recent context window.

## How to safely use AI agents for holiday shopping

DevFeed: [How to safely use AI agents for holiday shopping](<https://devfeed.tech/articles/how-to-safely-use-ai-agents-for-holiday-shopping-144198.md>)

Original publisher: [Read original article](<https://1password.com/blog/ai-agents-holiday-shopping>)

Author: info@1password.com (Rachel Sudbeck)

Published: 2026-11-19T00:00:00Z

Content type: tutorial

Language: en

Sources: [1Password](<https://devfeed.tech/sources/blog-on-1password-blog.md>)

Topics: [agentic commerce fraud](<https://devfeed.tech/topics/agentic-commerce-fraud.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Finance](<https://devfeed.tech/topics/finance.md>), [1Password](<https://devfeed.tech/topics/1password.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>)

Tags: [1password](<https://devfeed.tech/tags/1password.md>), [agent-identity](<https://devfeed.tech/tags/agent-identity.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [holiday](<https://devfeed.tech/tags/holiday.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [safely](<https://devfeed.tech/tags/safely.md>), [security](<https://devfeed.tech/tags/security.md>), [shopping](<https://devfeed.tech/tags/shopping.md>), [tips-advice](<https://devfeed.tech/tags/tips-advice.md>)

### AI overview

AI agents can help track holiday deals, but the article recommends keeping the shopper in control of account access and purchases. Its six steps are to verify assistants and extensions before connecting accounts; keep passwords and verification codes out of prompts, using a supported password manager integration where available; limit account access to what the task needs; set clear spending and product limits and enforce them through account controls; require human approval at checkout and review purchase details; and revoke access when shopping ends. The article warns that fake extensions may steal data or install malware, and prompt injection or agent errors may lead to unintended actions. It describes 1Password for Agents as letting users approve access to a specific login and fill credentials without exposing them to the agent; integration flows vary by agent provider.

### Source excerpt

Imagine: a no-budget, no-holds-barred shopping spree. You can just go online and buy whatever you want, with no limits. It's the dream of romcom protagonists and game show contestants alike. Of course, if you're the one signing the bill, it's more like a nightmare. And the fear of someone (or something) going wild with your bank balance has been at the core of recent conversations around AI agents. According to McKinsey & Company, over 50% of global consumers now use AI for shopping, and last year saw a 70% jump in the rate at which U.S. AI users completed a purchase with AI. However, a recent Salesforce survey revealed some important caveats to this trend: only 19% of personal agent users have used their agents at checkout, and 73% of shoppers aren't comfortable giving a personal AI agent their payment information. It's understandable why many people are turning to AI agents to help with their holiday shopping. For a human, it's almost a full-time job to track prices and sales across stores for everything on your list; an agent is far better equipped to keep an eye on offers for that collector's item your sister is asking for. You save energy, but can still pounce on the best deals when they're available. At the same time, it's natural that anyone who's shopping with agents this season would want to stay in control of what that agent can access. In this blog, we'll cover some of the risks of shopping online with AI agents, as well as how you can safely and confidently take advantage of them during this holiday season. We'll also be sharing key tips and advice from Dave Lewis, 1Password's Global Advisory CISO. 6 tips for safer holiday shopping with AI agents The key to shopping with agents is making sure you are always in control of what information (financial or otherwise) the agent can access. Here are some of the risks of using agents, and controls to rein in their access, so you don't have to find out just how expensive a "free agent" can be. 1. Verify your AI s

## Introducing Amazon OpenSearch Memory: Persistent memory for AI agents

DevFeed: [Introducing Amazon OpenSearch Memory: Persistent memory for AI agents](<https://devfeed.tech/articles/introducing-amazon-opensearch-memory-persistent-memory-for-ai-agents-141878.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/big-data/introducing-amazon-opensearch-memory-persistent-memory-for-ai-agents/>)

Author: Ganesh Natarajan

Published: 2026-11-18T20:50:32Z

Content type: release

Language: en

Sources: [AWS Big Data Blog](<https://devfeed.tech/sources/aws-big-data-blog.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [opensearch](<https://devfeed.tech/topics/opensearch.md>), [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.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>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-cloudwatch](<https://devfeed.tech/tags/amazon-cloudwatch.md>), [amazon-opensearch-serverless](<https://devfeed.tech/tags/amazon-opensearch-serverless.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [amazon-titan](<https://devfeed.tech/tags/amazon-titan.md>), [announcements](<https://devfeed.tech/tags/announcements.md>), [api](<https://devfeed.tech/tags/api.md>), [aws-sdk-for-python](<https://devfeed.tech/tags/aws-sdk-for-python.md>), [context](<https://devfeed.tech/tags/context.md>), [cross-session-memory](<https://devfeed.tech/tags/cross-session-memory.md>), [events](<https://devfeed.tech/tags/events.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [memory](<https://devfeed.tech/tags/memory.md>), [opensearch](<https://devfeed.tech/tags/opensearch.md>), [persistent-memory](<https://devfeed.tech/tags/persistent-memory.md>), [persistent-memory-for-ai](<https://devfeed.tech/tags/persistent-memory-for-ai.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [session](<https://devfeed.tech/tags/session.md>)

### AI overview

Amazon OpenSearch Memory adds persistent, cross-session memory to AI agents through serverless spaces containing verbatim events and memories derived from them. Applications write each turn and retrieve relevant memories or exact events before responding; event reads are immediate and searchability follows within seconds, while memory extraction runs asynchronously and may return no results for a new user at first. The service handles indexing, consolidation, retrieval, isolation, encryption, and retention, with actor and optional session controls; applications still add retrieved context to prompts and should review agent-written memories. In one LongMemEval-S run, the configured workflow used about 13,500 input tokens per question versus 167,000 for full history and scored 93.0% accuracy versus 95.2%; it beat BM25 raw-turn retrieval by 4.4 points. Results depend on the tested models and settings. General availability is in four AWS Regions.

### Source excerpt

Amazon OpenSearch Memory is now generally available. Built on Amazon OpenSearch Serverless, it adds persistent, cross-session memory to AI agents. It stores interactions as searchable events, derives memories, and retrieves relevant context, so you can give agents long-term memory without building your own memory system.

## What Is an Embedding? How AI Turns Meaning Into Numbers

DevFeed: [What Is an Embedding? How AI Turns Meaning Into Numbers](<https://devfeed.tech/articles/what-is-an-embedding-how-ai-turns-meaning-into-numbers-141932.md>)

Original publisher: [Read original article](<https://montecarlo.ai/blog-embedding>)

Author: Ruslan Sultanov

Published: 2026-11-18T18:58:12Z

Content type: article

Language: en

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

Topics: [vector embeddings in AI](<https://devfeed.tech/topics/vector-embeddings-in-ai.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [cosine similarity search](<https://devfeed.tech/topics/cosine-similarity-search.md>), [Data Quality](<https://devfeed.tech/topics/data-quality.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [clustering](<https://devfeed.tech/topics/clustering.md>)

Tags: [agent-trust](<https://devfeed.tech/tags/agent-trust.md>), [agent-trust-glossary](<https://devfeed.tech/tags/agent-trust-glossary.md>), [ai](<https://devfeed.tech/tags/ai.md>), [cosine-similarity](<https://devfeed.tech/tags/cosine-similarity.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embedding-model](<https://devfeed.tech/tags/embedding-model.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [embeddings-in-machine-learning](<https://devfeed.tech/tags/embeddings-in-machine-learning.md>), [embeddings-rag](<https://devfeed.tech/tags/embeddings-rag.md>), [glossary](<https://devfeed.tech/tags/glossary.md>), [meaning](<https://devfeed.tech/tags/meaning.md>), [text-embeddings](<https://devfeed.tech/tags/text-embeddings.md>), [vector-database](<https://devfeed.tech/tags/vector-database.md>), [vector-embeddings](<https://devfeed.tech/tags/vector-embeddings.md>), [what-is-an-embedding](<https://devfeed.tech/tags/what-is-an-embedding.md>)

### AI overview

Embeddings represent text, images, or other data as numeric vectors, placing semantically similar items near each other so systems can retrieve by meaning rather than exact wording. In a typical RAG pipeline, documents are split into chunks, embedded and indexed with metadata; a query is embedded to retrieve nearby passages for an LLM. Vectors are meaningful only within the model that produced them, and they become outdated when source content changes. Production reliability therefore depends on versioning vectors, re-embedding changed documents, removing deleted content, monitoring index freshness and evaluating and tracing retrieval. Stale or missing passages can lead an agent to give confident but outdated answers.

### Source excerpt

A customer types "can I send this back?" Your help center never uses that phrase. It talks about the "return window" and the "refund policy." Keyword search finds nothing. Yet a modern AI agent pulls up the right policy in milliseconds, because it isn't matching words. It's matching meaning. That's what embeddings do. This guide ...

## What Is Context Engineering? Giving AI Agents the Right Information

DevFeed: [What Is Context Engineering? Giving AI Agents the Right Information](<https://devfeed.tech/articles/what-is-context-engineering-giving-ai-agents-the-right-information-141931.md>)

Original publisher: [Read original article](<https://montecarlo.ai/blog-context-engineering>)

Author: Ruslan Sultanov

Published: 2026-11-18T18:46:57Z

Content type: article

Language: en

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

Topics: [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [context window](<https://devfeed.tech/topics/context-window.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Prompt Engineering](<https://devfeed.tech/topics/prompt-engineering.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [context](<https://devfeed.tech/topics/context.md>)

Tags: [agent-memory](<https://devfeed.tech/tags/agent-memory.md>), [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>), [context-engineering](<https://devfeed.tech/tags/context-engineering.md>), [context-engineering-for-ai-agents](<https://devfeed.tech/tags/context-engineering-for-ai-agents.md>), [context-engineering-vs-prompt-engineering](<https://devfeed.tech/tags/context-engineering-vs-prompt-engineering.md>), [context-engineering-vs-rag](<https://devfeed.tech/tags/context-engineering-vs-rag.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [context-window-management](<https://devfeed.tech/tags/context-window-management.md>), [data](<https://devfeed.tech/tags/data.md>), [data-pipeline](<https://devfeed.tech/tags/data-pipeline.md>), [data-quality](<https://devfeed.tech/tags/data-quality.md>), [glossary](<https://devfeed.tech/tags/glossary.md>), [llm-context](<https://devfeed.tech/tags/llm-context.md>), [prompts](<https://devfeed.tech/tags/prompts.md>), [what-is-context-engineering](<https://devfeed.tech/tags/what-is-context-engineering.md>)

### AI overview

Context engineering shapes everything an agent receives--instructions, retrieved data, tool results, and memory--so it has a small, relevant set of information at each step. Prompt engineering focuses on instruction wording; RAG fetches documents for the prompt; context engineering encompasses both, along with tool design, memory, and what to omit. Techniques include just-in-time retrieval, reranking and filtering, compressing long outputs, using sub-agents with separate context, storing notes externally, and structuring inputs. These cannot correct stale or faulty source data. The excerpt recommends monitoring freshness and volume, tracing outputs to source documents and versions, recording retrievals, and evaluating groundedness and correctness. It notes that larger context windows do not remove the need to select and manage information.

### Source excerpt

Two teams build the same support agent on the same model with nearly identical prompts. One answers correctly nine times out of ten. The other confidently quotes a shipping policy that changed in the spring. The difference isn't the model or the wording. It's what each agent was given to read before it answered. That's ...

## What's new for Genie in Microsoft: Copilot Cowork and Chat, Microsoft Teams, and Excel.

DevFeed: [What's new for Genie in Microsoft: Copilot Cowork and Chat, Microsoft Teams, and Excel.](<https://devfeed.tech/articles/what-s-new-for-genie-in-microsoft-copilot-cowork-and-chat-microsoft-teams-and-excel-140785.md>)

Original publisher: [Read original article](<https://www.databricks.com/blog/whats-new-genie-microsoft-copilot-cowork-and-chat-microsoft-teams-and-excel>)

Author: Kiriana Stukas; Toussaint Webb

Published: 2026-11-18T16:00:00Z

Content type: release

Language: en

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

Topics: [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Microsoft Teams](<https://devfeed.tech/topics/microsoft-teams.md>), [microsoft 365](<https://devfeed.tech/topics/microsoft-365.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [AI connector platforms](<https://devfeed.tech/topics/ai-connector-platforms.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [admin](<https://devfeed.tech/tags/admin.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-365](<https://devfeed.tech/tags/agent-365.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistants](<https://devfeed.tech/tags/ai-assistants.md>), [calendar](<https://devfeed.tech/tags/calendar.md>), [chat](<https://devfeed.tech/tags/chat.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [copilot-cowork](<https://devfeed.tech/tags/copilot-cowork.md>), [cowork](<https://devfeed.tech/tags/cowork.md>), [email](<https://devfeed.tech/tags/email.md>), [excel](<https://devfeed.tech/tags/excel.md>), [files](<https://devfeed.tech/tags/files.md>), [genie](<https://devfeed.tech/tags/genie.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [microsoft-copilot](<https://devfeed.tech/tags/microsoft-copilot.md>), [microsoft-teams](<https://devfeed.tech/tags/microsoft-teams.md>), [partners](<https://devfeed.tech/tags/partners.md>), [platform](<https://devfeed.tech/tags/platform.md>), [teams](<https://devfeed.tech/tags/teams.md>), [what-s-new](<https://devfeed.tech/tags/what-s-new.md>)

### AI overview

Genie brings governed Azure Databricks data and business context into Microsoft Copilot Chat and Cowork, Teams, Excel, and Copilot Studio. Genie Ontology combines team-defined semantics such as certified definitions and metric views with context learned from dashboards, queries, and documents; it is described as generally available. Unity Catalog applies each user's data permissions, while Unity Gateway provides MCP policies, traces, and budget controls. In Teams, users can message Genie or mention it in a chat; Genie One is the default, and conversations can be pinned to a Genie Agent to scope answers to that agent's curated data and instructions. Teams setup requires an admin to add the app and set response visibility; users sign in to Databricks and choose a workspace. Private Link requires a context-based ingress policy. The Excel add-in answers plain-English questions with citations and can load results into workbooks. The Copilot Cowork plugin requires users to enable it, connect, and sign in, with no OAuth app registration or manifest edits. The native Teams app is the default choice described; Copilot Studio suits custom agents combining Genie Agents with other tools. Work

### Source excerpt

Most AI assistants can read a person's email, files, and calendar, but it can't tell...

## TBM 452: Contexting vs. Context

DevFeed: [TBM 452: Contexting vs. Context](<https://devfeed.tech/articles/tbm-452-contexting-vs-context-141412.md>)

Original publisher: [Read original article](<https://cutlefish.substack.com/p/tbm-452-contexting-vs-context>)

Author: John Cutler

Published: 2026-11-18T07:00:16Z

Content type: article

Language: en

Sources: [The Beautiful Mess](<https://devfeed.tech/sources/the-beautiful-mess.md>)

Topics: [context](<https://devfeed.tech/topics/context.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [meetings](<https://devfeed.tech/topics/meetings.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-context](<https://devfeed.tech/tags/ai-context.md>), [cognition](<https://devfeed.tech/tags/cognition.md>), [collaboration](<https://devfeed.tech/tags/collaboration.md>), [context](<https://devfeed.tech/tags/context.md>), [decision](<https://devfeed.tech/tags/decision.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [developing](<https://devfeed.tech/tags/developing.md>), [embedded](<https://devfeed.tech/tags/embedded.md>), [experimentation](<https://devfeed.tech/tags/experimentation.md>), [frameworks](<https://devfeed.tech/tags/frameworks.md>), [humans](<https://devfeed.tech/tags/humans.md>)

### AI overview

Experts often rely on tacit knowledge and rapid pattern recognition, so explaining their reasoning on demand can be difficult even when their judgment is strong. Context-sharing can break down when people cannot state what they need or already know, expect different levels of detail, or interpret clarifying questions as challenges to competence. Clear explanations are not the only way to share expertise: working alongside someone, observing, practicing, and discussing real decisions can build shared understanding. The article argues that cognition develops through interaction with people, environments, and tools, and questions the assumption that AI context must always be made explicit and structured. It suggests designing AI to join collaborative work, while recounting a team that resolved an overcomplicated effort to supply AI context by simply meeting.

### Source excerpt

I have observed highly experienced people struggle to describe their expertise, the information they needed (or used), the decisions they needed to make (or made), and what they know about a situation.

[Next page](<https://devfeed.tech/topics/ai-context-management.md?cursor=WyIyMDI2LTExLTE4VDA3OjAwOjE2KzAwOjAwIiwgImViZjFkNzU4LThhYTYtNDA2Zi1iNTMxLTM3MTQ0OWFhNjAyMyJd>)