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

Less Context, Better Agents: Efficient Context Engineering for Long-Horizon Tool-Using LLM Agents
Jun 8, 2026Abhilasha Lodha, Mahsa Pahlavikhah Varnosfaderani, Abir Chakraborty +1LLM Inference Efficiency Tool-Augmented Language Model Agents
Microsoft
Context Rot in AI-Assisted Software Development: Repurposing Documentation Consistency for AI Configuration Artifacts
Jun 8, 2026Christoph Treude, Sebastian BaltesSoftware Engineering LLM Context Management
Singapore Management University · Singapore, Singapore · Heidelberg University +1
Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents
Jun 6, 2026Xinyu Guan, Qianyang Zhao, Yuming DengLLM Agent Memory LLM Context Management
Alibaba Group, China
Customer-Agent: Overcoming Context Limitations in Ultra-Long Shopping Trajectories via Tool-Augmented Agents and RLVR
Jun 6, 2026Hongye Liu, Rongmei Lin, Anurag Kashyap +4Tool-Augmented Language Model Agents Long-Context Modeling
Amazon · Duke University
NTILC: Neural Tool Invocation via Learned Compression
Jun 4, 2026Andrew Krikorian, Yayuan Li, Jason J. CorsoLLM Inference Acceleration LLM Tool Use
Department of Robotics University of Michigan Ann Arbor, MI 48104 · Department of ECE University of Michigan Ann Arbor, MI 48104
TokenMizer: Graph-Structured Session Memory for Long-Horizon LLM Context Management
Jun 4, 2026Shweta MishraLLM Agent Memory LLM Context Management
Independent Researcher, India.
Microskill Architecture: A Modular Skill-Driven Framework for AI-Native Code Generation
Jun 4, 2026Mohammad Zare, Omid AbdolrahmaniAI Coding Agents Agentic Code Generation
Artificial Intelligence Laboratory at AriooBarzan Engineering Team, Shiraz, Iran
EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management
Jun 2, 2026Zherui Yang, Fan Liu, Yansong Ning +1Agentic RL LLM Agent Skill Learning
The Hong Kong University of Science and Technology (Guangzhou)
Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines
Jun 2, 2026Justice Owusu Agyemang, Jerry John Kponyo, Kwame Opuni-Boachie Obour Agyekum +3LLM Compression Token Pruning
1VIA Cybersecurity Lab, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana · 2Quantum and Assistive Technologies Lab, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana
Absorbing Complexity: An Interaction-Native Knowledge Harness for Financial LLM Agents
Jun 1, 2026Ailiya Borjigin, Igor Stadnyk, Ben Bilski +4LLM Agent Memory LLM Agents
True Trading
SkillPager: Query-Adaptive Intra-Skill Navigation via Semantic Node Retrieval
May 30, 2026Zicai Cui, Zihan Guo, Weiwen Liu +1LLM Agent Skill Retrieval LLM Agents
Shanghai Jiao Tong University · Shanghai Innovation Institute · Sun Yat-sen University
Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism
May 29, 2026Haoxiang Zhang, Qixin Xu, Zhuofeng Li +4Agentic Search Agentic Retrieval
1UC San Diego · 2UC Berkeley · 3Texas A&M University +1
CoMem: Context Management with A Decoupled Long-Context Model
May 29, 2026Yuwei Zhang, Chengyu Dong, Shuowei Jin +11LLM Inference LLM Inference Acceleration
Halıcıoğlu Data Science Institute, University of California, San Diego · Amazon
Learning Agent-Compatible Context Management for Long-Horizon Tasks
May 29, 2026Lu Yi, Runlin Lei, Liuyi Yao +6Long-Horizon Agent Tasks LLM Context Management
1Renmin University of China · Work done during internship at Tongyi Lab, Alibaba Group · 2Tongyi Lab, Alibaba Group +2
When Should Models Change Their Minds? Contextual Belief Management in Large Language Models
May 28, 2026Haoming Xu, Weihong Xu, Zongrui Li +6Representation Steering Belief Updating in LLMs
♠Zhejiang University · ♣HomologyAI
Enhancing Multi-Agent Communication through Attention Steering with Context Relevance
May 28, 2026Hongxiang Zhang, Yuan Tian, Tianyi ZhangMulti-Agent LLM Systems Multi-Agent System Optimization
Purdue University West Lafayette, IN, USA
Indexing the Unreadable: LLM-Native Recursive Construction and Search of Service Taxonomies
May 28, 2026Wei Zheng, Yang Yan, Yiyang Shao +6LLM Agents Information Retrieval
openJiuwen A2X
Context Distillation as Latent Memory Management
May 27, 2026Ziyang Zheng, Zeju Li, Xiangyu Wen +5Memory-Augmented Language Models Language Model Distillation
The Chinese University of Hong Kong · Huawei Noah’s Ark Lab
ContextGuard: Structured Self-Auditing for Context Learning in Language Models
May 26, 2026Hongbo Jin, Chi Wang, Haoran Tang +5LLM Auditing Instruction Following
Peking University · SCUT · Tsinghua University
Bounded Path Context: A Controlled Study of Visible Path History in LLM-Based Knowledge Graph Question Answering
May 26, 2026Xihang Shan, Ye LuoMulti-Hop QA LLM Reasoning with Graphs
School of Mathematical Sciences Xiamen University · School of Informatics Xiamen University
LogDx-CI: Benchmarking Log Reduction Tools for LLM Root-Cause Diagnosis
May 26, 2026Bowen QinLLM Agent Evaluation AI Agent Benchmarks
National University of Singapore
Tool-Schema Compression Enables Agentic RAG Under Constrained Context Budgets
May 24, 2026Furkan SakizliTool-Augmented Language Model Agents Agentic RAG
Independent Researcher
Parallel Context Compaction for Long-Horizon LLM Agent Serving
May 22, 2026Musa Cim, Burak Topcu, Chita Das +1LLM Inference Efficiency LLM Agent Workflow Optimization
The Pennsylvania State University
The Efficiency Frontier: A Unified Framework for Cost-Performance Optimization in LLM Context Management
May 21, 2026Binqi Shen, Lier Jin, Hanyu Cai +2LLM Evaluation Cost-Aware Inference
Department of Industrial Engineering and Management Sciences Northwestern University Evanston, USA · Fuqua School of Business Duke University Durham, USA · Department of Engineering Carnegie Mellon University Pittsburgh, USA +1
RMA: Context-Orchestrated Research Math Agents
May 20, 2026Zelin Zhao, Bo Yuan, Yuchen Zhu +2LLM Context Management LLM Mathematical Reasoning
Georgia Institute of Technology
PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents
May 19, 2026Zhuohan Gu, Qizheng Zhang, Omar Khattab +1LLM Agent Memory Long-Context Inference
MIT CSAIL · Stanford University
Position: The Turing-Completeness of Autoregressive Transformers Relies Heavily on Context Management
May 19, 2026Guanyu Cui, Zhewei Wei, Kun HeTransformer Expressivity Transformer
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China · DEKE Lab, Renmin University of China, Beijing, China
Compress the Context, Keep the Commitments: A Formal Framework for Verifiable LLM Context Compression
May 17, 2026Natalia Trukhina, Vadim VashkelisLLM Compression LLM Context Management
Embedded Intelligence Lab (EMILAB)
LLMs in Qualitative Research: Opportunities, Limitations, and Practical Considerations
May 15, 2026Henry Salgado, Meagan R. Kendall, Martine Ceberio +1LLM Prompting LLM Context Management
Contexting as Recommendation: Evolutionary Collaborative Filtering for Context Engineering
May 15, 2026Jiachen Zhu, Zhuoying Ou, Congmin Zheng +9LLM Prompting LLM Routing
Shanghai Jiao Tong Univ. · Univ. College London · Carnegie Mellon Univ. +1

Jun 8, 2026, cs.AIJ/K move · Enter open · S save

Less Context, Better Agents: Efficient Context Engineering for Long-Horizon Tool-Using LLM Agents

Abhilasha Lodha, Mahsa Pahlavikhah Varnosfaderani, Abir Chakraborty, Abhinav Mithal

Microsoft

LLM Inference Efficiency Tool-Augmented Language Model Agents LLM Agent Workflow Optimization LLM Tool Use Long-Horizon LLM Agents LLM Context Management+2

Open paper AskPDF arXiv

Large language models deployed as autonomous agents for enterprise workflows face a key challenge: verbose tool responses from enterprise systems can cause context overflow, stale-state errors, and high inference cost. We study this problem in automated expense itemization in Microsoft Dynamics 365 Finance and Operations using Model Context Protocol tools. We evaluate four GPT-5 configurations on a 50-task hotel expense benchmark: no user model, full conversation history, context pruned to the last 5 tool call/response pairs, and pruning with automated summarization. Results are averaged across 5 independent runs, with the user model held constant for the context-engineering comparison. The no-user-model baseline achieves only 8.0% complete itemization. Full-context retention improves completion to 71.0%, but consumes 1,480,996 tokens and 14.56 hours per benchmark. Pruning to the last 5 tool calls improves completion to 79.0% while reducing token use to 535,274 and runtime to 5.39 hours. Adding summarization achieves the best result: 91.6% complete itemization and 99.64% average amount itemized, with 553,374 tokens and 5.79 hours. We further report confidence intervals, effect-size analysis, sensitivity over pruning and summary windows, failure analysis, results across five expense types grouped into three categories, and cross-model evidence with Claude Sonnet 4.5. These results show that, for this class of enterprise tool-use workflow, selective retention of recent tool interactions plus compact summarization can improve both reliability and efficiency compared with full-history retention.

Momentum

Related topics

Latest papers 156