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.

Architecting AgentOS: From Token-Level Context to Emergent System-Level Intelligence
Feb 24, 2026ChengYou Li, XiaoDong Liu, XiangBao Meng +1Cognitive Architectures for AI Agents LLM Context Management
Yishu Research · Fukuoka Institute of Technology, Japan · National University of Singapore
Structured Prompt Language: Declarative Context Management for LLMs
Feb 23, 2026Wen G. GongLLM Prompting LLM Context Management
Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?
Feb 12, 2026Thibaud Gloaguen, Niels Mündler-Sasahara, Mark Niklas Müller +2AI Coding Agents Coding Agents
Department of Computer Science ETH Zurich
To Retrieve or To Think? Cross-Boundary Context Evolution for Multi-hop Complex Reasoning
Jan 13, 2026Rubing Chen, Jian Wang, Wenjie Li +2Multi-Hop QA Retrieval-Augmented Generation
Department of Computing, The Hong Kong Polytechnic University
CaveAgent: Transforming LLMs into Stateful Runtime Operators
Jan 4, 2026Maohao Ran, Zhenglin Wan, Cooper Lin +21LLM Agent Memory LLM Agents
HKUST · HKBU · NUS +8
AOI: Context-Aware Multi-Agent Operations via Dynamic Scheduling and Hierarchical Memory Compression
Dec 15, 2025Zishan Bai, Hanxuan Chen, Jiayi Gu +9Multi-Agent Orchestration LLM Context Management
Columbia University · Hunan University · Central University of Finance and Economics +8
Role-aware Heuristic Episodic Attention for Conversational LLMs
Dec 7, 2025Wanyang Hong, Zhaoning Zhang, Yi Chen +5LLM Context Management Memory-Augmented Language Models
National Key Laboratory of Parallel and Distributed Computing College of Computer Science and Technology National University of Defense Technology, Changsha, China.
Lost in the Maze: Overcoming Context Limitations in Long-Horizon Agentic Search
Oct 21, 2025Howard Yen, Yoonsang Lee, Ashwin Paranjape +5Agentic Search Long-Horizon Agent Evaluation
Princeton Language and Intelligence, Princeton University · Work done as an intern at Samaya AI. · Samaya AI
RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory
Aug 6, 2025Jun Liu, Zhenglun Kong, Changdi Yang +12LLM Context Management Multi-Agent LLM Systems
Carnegie Mellon University · Northeastern University · Harvard University +5
InComeS: Integrating Compression and Selection Mechanisms into LLMs for Efficient Model Editing
May 28, 2025Shuaiyi Li, Zhisong Zhang, Yang Deng +6In-Context Learning Model Editing
The Chinese University of Hong Kong · City University of Hong Kong · Singapore Management University +1
Knowing When to Stop: Efficient Context Processing via Latent Sufficiency Signals
Feb 3, 2025Roy Xie, Junlin Wang, Paul Rosu +4LLM Context Management Long-Context Language Model Inference
Duke · Rice · JHU +1

Feb 24, 2026J/K move · Enter open · S save

Architecting AgentOS: From Token-Level Context to Emergent System-Level Intelligence

ChengYou Li, XiaoDong Liu, XiangBao Meng, XinYu Zhao

Yishu Research · Fukuoka Institute of Technology, Japan · National University of Singapore

Cognitive Architectures for AI Agents LLM Context Management LLM Agent Orchestration

Open paper AskPDF arXiv

The paradigm of Large Language Models is undergoing a fundamental transition from static inference engines to dynamic autonomous cognitive systems.While current research primarily focuses on scaling context windows or optimizing prompt engineering the theoretical bridge between micro scale token processing and macro scale systemic intelligence remains fragmented.This paper proposes AgentOS,a holistic conceptual framework that redefines the LLM as a "Reasoning Kernel" governed by structured operating system logic.Central to this architecture is Deep Context Management which conceptualizes the context window as an Addressable Semantic Space rather than a passive buffer.We systematically deconstruct the transition from discrete sequences to coherent cognitive states introducing mechanisms for Semantic Slicing and Temporal Alignment to mitigate cognitive drift in multi-agent orchestration.By mapping classical OS abstractions such as memory paging interrupt handling and process scheduling onto LLM native constructs, this review provides a rigorous roadmap for architecting resilient scalable and self-evolving cognitive environments.Our analysis asserts that the next frontier of AGI development lies in the architectural efficiency of system-level coordination.