LLM Context Management

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

23 papers in the last four weeks, up 92% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 156

All topics

Curating Always-Loaded Context for LLM Agents: A Capacitated Assortment Model with Censored Feedback
Oct 7, 2026Zexuan Liu, Yuning Yang, Tiancheng ZhaoLLM Context Management LLM Agents
University of Illinois at Urbana-Champaign · Georgia Institute of Technology · Saint Louis University
Decoupling Logic from Persona: Structural Immunity of Edge LLM Agents to Context Pollution
Oct 7, 2026Masaaki Nakatsu, Reno WangLLM Inference LLM Context Management
AO, Inc. / OrbLabs AG · AO, Inc.
ReFold: Training-Free Reversible Inter-Turn Context Folding for Long-Horizon Agents
Oct 6, 2026Yupeng Su, Jiayi Tian, Zheng Zhang +1LLM Inference Efficiency Long-Context Language Model Inference
University of California, Santa Barbara · Intel
When Agent Context Goes Stale: Incoherence in Volatile Agent Context
Oct 4, 2026Yingying Liu, Junzhou Fang, Chenxiong QianLLM Context Management LLM Agent Reliability
The University of Hong Kong Hong Kong SAR, China
Decoupling Memory from Context: Structured Memory for Token-Efficient Test-Time Continual Learning
Oct 2, 2026Yehya Farhat, Michael Desmond, Anastasios KyrillidisContinual Learning for LLM Agents Continual Learning for LLMs
Rice University, Department of Computer Science Houston, TX, USA · IBM Research Yorktown Heights, NY, USA
The Persona Is Still There, but Who Is Speaking? Latent Identity Reversion in Persistent AI Agents
Oct 1, 2026David Fraile NavarroPersona Consistency Personality Modeling in Language Models
Centre for Health Informatics, Australian Institute of Health Innovation Macquarie University, Sydney, Australia
Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States
Oct 1, 2026Yu Luo, Jiamin Jiang, Yimin Zuo +9Belief Updating in LLMs Long-Horizon LLM Agents
Nankai University · Alibaba Group · Tsinghua University
Role-aware Heuristic Episodic Attention for Conversational LLMs
Oct 1, 2026Wanyang Hong, Zhaoning Zhang, Yi Chen +5Memory-Augmented Language Models Long-Context Language Model Inference
National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, National University of Defense Technology, Changsha, China.
Can LLMs Reason Over Long Horizons? An Empirical Evaluation of Context Strategies for Longitudinal Clinical Reasoning
Sep 30, 2026Taye Akinrele, Noorbakhsh Amiri Golilarz, Subash Neupane +2Long-Context Language Model Evaluation Clinical Reasoning
Department of Computer Science, The University of Alabama
When Context Changes: Understanding Update Failures in LLMs
Sep 30, 2026Junyu Guo, Yuchen Fang, Shangding Gu +3Belief Updating in LLMs Attention Mechanisms
University of California, Berkeley
ContextRender: From Execution Dependencies to Agent Context
Sep 29, 2026Savini Kashmira, Jayanaka L. Dantanarayana, Lingjia Tang +1Graph-Based Agent Memory Long-Horizon LLM Agents
University of Michigan, Ann Arbor, USA
Context Language Models
Sep 29, 2026Rulin Shao, Shannon Zejiang Shen, Junjie Oscar Yin +10Memory-Augmented Language Models LLM Context Management
University of Washington · Meta Superintelligence Labs · MIT +1
FOCUS: Training-Free Decision-Preserving Context Compression for LLM Agents
Sep 29, 2026Shantanu Dixit, Anson Bastos, Xuchao Zhang +2Long-Horizon LLM Agents LLM Context Management
M365 Research, Microsoft
CADOC: Cache-Aware Dynamic Object Context for Long-Horizon Agents
Sep 29, 2026Junjie Yao, Zhangchen Zhou, Zhi-Qin John XuCost-Aware Inference Prefix Caching
School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai, China. · Institute of Natural Sciences, Shanghai Jiao Tong University, Shanghai, China.
CoEM: Empowering Long-Context Reasoning with Commit-on-Evidence Memory
Sep 29, 2026Jingguang Li, Yebo Wu, Zuyi Guo +7Memory-Augmented Language Models Persistent Memory for Language Models
Korea Advanced Institute of Science & Technology · University of Macau · Massachusetts Institute of Technology
Continuous Context Management
Sep 28, 2026William Hoy, Jingxuan Fan, Nurcin Celik +1Context Distillation Long-Horizon LLM Agents
University of Miami · Harvard University
Beyond Skill Evolution: Self-Evolving Context Management Policies for Long-Horizon Agent Harnesses
Sep 28, 2026Weiyuan Li, Jinghan Xu, Aili Chen +4Agent Harness Optimization Long-Horizon Agent Tasks
School of Data Science, Fudan University · Shanghai Key Laboratory of Data Science · College of Computer Science and Artificial Intelligence, Fudan University
FlowState: Execution State as Memory for Long-Horizon LLM Agents
Sep 28, 2026Minghao Li, Bangyan Li, Zifan Wang +5LLM Agent Memory Long-Horizon LLM Agents
Ant International, Ant Group
Adaptive Consistency Graph for Long-Horizon Agents
Sep 26, 2026Jiecong Wang, Hao Peng, Zhanyi WangLong-Horizon Agent Evaluation Graph-Based Agent Memory
Beihang University · QI-ANXIN GROUP
Realize What Matters: Principled Context Representation for Large-Scale Reasoning
Sep 23, 2026Michael Theologitis, Dean Light, Shuyue Stella Li +3Long-Context Inference LLM Context Management
University of Washington
Deploying Foundation Models for Embodied Navigation
Sep 22, 2026Vishnu Sashank Dorbala, Dinesh ManochaEmbodied Navigation Large Language Model-Based Robot Planning
University of Maryland, College Park
Clarification Is Not Correction: LLMs Fail to Let Go
Sep 21, 2026Jianzhe Lin, Xiaolin Li, Fei Wang +3LLM Reliability LLM Context Management
MetaAI
An Empirical Study of Harness Design for Coding Agents
Sep 17, 2026Run-Ze Fan, Zihao Zhang, Simin Ma +6Coding Agents Agent Harness Optimization
UMass Amherst · Emory University · UNC Charlotte
Pull: Lazy Materialization of Working Memory for Stateful LLM Conversations
Sep 13, 2026Jiangang ChenLLM Inference Efficiency LLM Memory
Chengdu Beiluoshimen Technology Co., Ltd.
Kernel-Managed Shared Memory for System-Wide Personalization
Sep 9, 2026Ryan Lum, Yongfeng ZhangMulti-Agent LLM Systems AI Agent Governance
Department of Computer Science Rutgers University Piscataway, NJ 08854
Context operations to architecture modelling output from large language models and evaluation criteria for their use in systems engineering design
Sep 9, 2026Vinicius Kaster Marini, Petter KrusSoftware Engineering Model-Based Systems Engineering
Department of Mechanical Engineering Centre of Technology Federal University of Santa Maria Santa Maria/RS, BR 97105-900, Brazil · Section for Fluid Power and Mechatronics Department of Management and Engineering Linköping University SE 581 83, Linköping, Sweden
The Analyst in the Prompt: Role, Retrieval, and Memory Biases in LLM Financial Analysis
Sep 2, 2026Ahmed Asaad, Amr Mohamed, Yang Zhang +1LLM Evaluation LLM Auditing
Durham University Business School · MBZUAI & Ecole Polytechnique · Ecole Polytechnique +1
Architecting Conversational Data Systems for Stateless LLM APIs: The Hydration Proxy Pattern
Sep 1, 2026Joseph AxisaLLM Grounding LLM Serving
Google Cloud · California, USA
LatentPress: Context Compression Beyond Text and Vision
Sep 1, 2026Zhengze Zhou, Hejian SangLLM Inference Acceleration LLM Context Management
1Cornell University · 2Iowa State University
ClinTraceBench: Source-Verifiable Longitudinal Clinical Reasoning over EHR-Derived Dialogues
Sep 1, 2026Huimin Wang, Zhengyi Zhao, Yutian ZhaoClinical QA Clinical Reasoning
Shenzhen University · The Chinese University of Hong Kong · Dealism

Oct 7, 2026, cs.AIJ/K move · Enter open · S save

Curating Always-Loaded Context for LLM Agents: A Capacitated Assortment Model with Censored Feedback

Zexuan Liu, Yuning Yang, Tiancheng Zhao

University of Illinois at Urbana-Champaign · Georgia Institute of Technology · Saint Louis University

LLM Context Management LLM Agents Assortment Optimization

Open paper AskPDF arXiv

At the start of every session, LLM agents load a fixed context file, such as

\texttt{AGENTS.md}

. Each loaded token in the file is charged again in every later round of the session, and these files can degrade performance as they grow in size. However, in practice, human or automated curators usually grow these files by appending. We formulate context curation as a capacitated assortment problem. Instructions consume tokens under a finite attention capacity; adding an instruction never raises the compliance of the others, while retained instructions incur a per-session setup cost. We prove an upper bound on the optimal file size, regardless of the number of available candidate instructions, and that appending every instruction with positive standalone value can be arbitrarily worse in net value than selecting an optimal subset. A token budget also limits the loss when the token price is underestimated. We then examine what can be learned from past sessions and how this information can guide decisions to add or remove instructions. Feedback is inherently censored: the benefits and harms of loaded instructions are observable, whereas missing instructions generate feedback only when their absence causes harm. In this setting, we show that deleting instructions ignored by agents can inevitably remove helpful ones. We characterize how much evidence should be collected before adding an instruction. Besides, we bound regret when human reviewers can inspect only a limited number of edits per period. Empirical experiments further show that irrelevant rules drawn from real context files reduce language-model compliance.

Momentum

Related topics

Latest papers 156