LLM Context Management

LLM: Large Language Model

This field studies how language models and agents can use conversation history, documents, tool outputs, and memory when their working context is limited or grows costly. Common approaches include truncation and summarization, relevance-based retrieval, structured or external memory, and adaptive policies that decide what to retain, restore, or discard; some systems also manage attention or KV-cache state directly. Methods are tested on tasks such as long-horizon search, coding, multi-turn question answering, and tool use. The central tension is reducing tokens, latency, and cost without losing evidence, dependencies, or safety constraints needed for later decisions, and results vary substantially by task and model.

Latest papers

251 papers37 papers in the last four weeks, up 48% on the four weeks before. 0.2% of all new papers.

Can LLMs Take Retrieved Information with a Grain of Salt?
May 7, 2026Behzad Shayegh, Mohamed Osama Ahmed, Fred Tung +1Retrieval-Augmented Generation LLM Evaluation
RBC Borealis
From History to State: Constant-Context Skill Learning for LLM Agents
May 6, 2026Haoyang Xie, Xinyuan Wang, Yancheng Wang +2LLM Agent Skill Learning LLM Agent Training
School of Computing and Augmented Intelligence, Arizona State University
LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents
May 6, 2026Yijun Lu, Rui Ye, Yuwen Du +3Web Search Agents Tool-Using Agents
Shanghai Jiao Tong University
When Context Hurts: The Crossover Effect of Knowledge Transfer on Multi-Agent Design Exploration
May 5, 2026Saranyan VigrahamSoftware Engineering Agents LLM Agent Orchestration
Meta
Perturbation Dose Responses in Recursive LLM Loops: Raw Switching, Stochastic Floors, and Persistent Escape under Append, Replace, and Dialog Updates
May 4, 2026Pawel KaplanskiLanguage Model Robustness LLM Context Management
Kaplanski AI Lab · Kaplanski Ai Lab
A Language for Describing Agentic LLM Contexts
May 3, 2026Noga Peleg Pelc, Gal A. Kaminka, Yoav GoldbergLLM Prompting LLM Agents
Dept. of Computer Science and AI Bar-Ilan University
Beyond Compaction: Structured Context Eviction for Long-Horizon Agents
May 1, 2026Andrew Semenov, Svyatoslav DorofeevLong-Horizon LLM Agents LLM Context Management
Kiz8
Context Recycling for Long-Horizon LLM Inference
May 1, 2026Derek ThomasLLM Inference Efficiency Long-Context Language Model Inference
Independent Researcher · contextforge
Budget-Aware Routing for Long Clinical Text
May 1, 2026Khizar Qureshi, Geoffrey Martin, Yifan PengSubmodular Optimization Long-Context Language Model Inference
MIT, Cambridge, MA · Cornell University, Ithaca, NY · Weill Cornell Medicine, New York, NY
CL-bench Life: Can Language Models Learn from Real-Life Context?
Apr 29, 2026Shihan Dou, Yujiong Shen, Chenhao Huang +35LLM Evaluation LLM Grounding
Hunyuan Team, Tencent · Fudan University
Dont Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination
Apr 27, 2026Prafulla Kumar Choubey, Kung-Hsiang Huang, Pranav Narayanan Venkit +5Deep Research Agents LLM Agent Orchestration
Salesforce AI Research
ContextWeaver: Selective and Dependency-Structured Memory Construction for LLM Agents
Apr 24, 2026Yating Wu, Yuhao Zhang, Sayan Ghosh +4LLM Agent Memory Graph-Based Agent Memory
UT Austin · AWS AI Labs
Tool Attention Is All You Need: Dynamic Tool Gating and Lazy Schema Loading for Eliminating the MCP/Tools Tax in Scalable Agentic Workflows
Apr 23, 2026Anuj Sadani, Deepak KumarGated Attention LLM Tool Use
CogniConsole: Externalizing Inference-Time Control as a Formal Abstraction for Reliable LLM Interactions
Apr 21, 2026Vanessa Figueiredo, Wilter FranceschiAI Agent Reliability Language Model-Based Control
Orbital Sea Regina, SK, Canada
Context: Proactive Goal-Directed Intelligence via Composable Sandboxed Programs, Declarative Wiring, and Structured Interaction
Apr 21, 2026Gregory MagarshakAI Agent Governance LLM Agent Orchestration
Qbix, Inc. & Intercoin, Inc. · New York, USA · Also with IE University NYC.
LANTERN: Layered Archival and Temporal Episodic Retrieval Network for Long-Context LLM Conversations
Apr 18, 2026Rahul SubramaniMemory-Augmented Language Models Persistent Memory for Language Models
Cisco Systems, Inc.
GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)
Apr 18, 2026Jiaqing Liang, Jinyi Han, Weijia Li +15Tool-Augmented Language Model Agents LLM Agent Memory
Advantage AI Agent Lab (A3 Lab)
Consistency Analysis of Sentiment Predictions using Syntactic & Semantic Context Assessment Summarization (SSAS)
Apr 16, 2026Sharookh Daruwalla, Nitin Mayande, Shreeya Verma Kathuria +2Sentiment Analysis Language Model Robustness
1Tellagence Inc.∗ · 2Villanova School of Business, Villanova University† · 3Maseeh College of Engineering and Computer Science, Portland State University‡
Cooperative Memory Paging with Keyword Bookmarks for Long-Horizon LLM Conversations
Apr 14, 2026Ziyang LiuLLM Context Management Long-Term Conversational Memory
Independent Researcher
SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context
Apr 13, 2026Shuquan Lian, Juncheng Liu, Yazhe Chen +2Software Engineering Agents Agentic Reasoning
Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China, Xiamen University · Microsoft
Context Kubernetes: Declarative Orchestration of Enterprise Knowledge for Agentic AI Systems
Apr 13, 2026Charafeddine MouzouniAI Agent Governance LLM Context Management
OPIT – Open Institute of Technology, and Cohorte AI, Paris, France.
Escaping the Context Bottleneck: Active Context Curation for LLM Agents via Reinforcement Learning
Apr 13, 2026Xiaozhe Li, Tianyi Lyu, Yizhao Yang +6Lost-in-the-Middle Effect LLM Context Management
Tongji University · CurrentsAI Research · Stanford University +1
ClawVM: Harness-Managed Virtual Memory for Stateful Tool-Using LLM Agents
Apr 11, 2026Mofasshara Rafique, Laurent BindschaedlerLLM Context Management Agent Memory Management
Independent Researcher Switzerland · Max Planck Institute for Software Systems Saarbrücken, Saarland, Germany
SinkTrack: Attention Sink based Context Anchoring for Large Language Models
Apr 11, 2026Xu Liu, Guikun Chen, Wenguan WangLLM Context Management LLM Hallucination Mitigation
The State Key Lab of Brain-Machine Intelligence, Zhejiang University
MEMENTO: Teaching LLMs to Manage Their Own Context
Apr 10, 2026Vasilis Kontonis, Yuchen Zeng, Shivam Garg +7LLM Context Management Efficient Language Model Reasoning
Microsoft Research
MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversation
Apr 9, 2026Jyotika Singh, Fang Tu, Miguel Ballesteros +6LLM Context Management
Oracle AI
Dynamic Attentional Context Scoping: Agent-Triggered Focus Sessions for Isolated Per-Agent Steering in Multi-Agent LLM Orchestration
Apr 9, 2026Nickson PatelMulti-Agent LLM Systems LLM Agent Orchestration
Independent Researcher
CLEAR: Context Augmentation from Contrastive Learning of Experience via Agentic Reflection
Apr 8, 2026Linbo Liu, Guande Wu, Han Ding +7LLM Context Management LLM Agents
AWS AI
Short Data, Long Context: Distilling Positional Knowledge in Transformers
Apr 7, 2026Patrick Huber, Ernie Chang, Chinnadhurai Sankar +4Long-Context Language Modeling LLM Context Management
Meta Reality Labs
Context-Agent: Dynamic Discourse Trees for Non-Linear Dialogue
Apr 7, 2026Junan Hu, Shudan Guo, Wenqi Liu +2LLM Context Management Multi-Turn Dialogue Evaluation
Shandong University, China

May 7, 2026J/K move · Enter open · S save

Can LLMs Take Retrieved Information with a Grain of Salt?

Behzad Shayegh, Mohamed Osama Ahmed, Fred Tung, Leo Feng

RBC Borealis

Retrieval-Augmented Generation LLM Evaluation LLM Uncertainty Estimation Language Model Robustness LLM Context Management

Open paper AskPDF arXiv

Large language models have demonstrated impressive retrieval-augmented capabilities. However, a crucial area remains underexplored: their ability to appropriately adapt responses to the certainty of the retrieved information. It is a limitation with real consequences in high-stakes domains like medicine and finance. We evaluate eight LLMs on their context-certainty obedience, measuring how well they adjust responses to match expressed context certainty. Our analysis reveals systematic limitations: LLMs struggle to recall prior knowledge after observing an uncertain context, misinterpret expressed certainties, and overtrust complex contexts. To address these, we propose an interaction strategy combining prior reminders, certainty recalibration, and context simplification. This approach reduces obedience errors by 25% on average, without modifying model weights, demonstrating the efficacy of interaction design in enhancing LLM reliability. Our contributions include a principled evaluation metric, empirical insights into LLMs' uncertainty handling, and a portable strategy to improve context-certainty obedience across diverse LLMs.