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.

HYVE: Hybrid Views for LLM Context Engineering over Machine Data
Apr 7, 2026Jian Tan, Fan Bu, Yuqing Gao +5LLM Context Management LLM Inference Efficiency
Cisco Systems, Inc., San Jose, California, USA
Decocted Experience Improves Test-Time Inference in LLM Agents
Apr 6, 2026Maohao Shen, Kaiwen Zha, Zexue He +6LLM Context Management Memory-Augmented Language Model Agents
Massachusetts Institute of Technology · Stanford University · MIT-IBM Watson AI Lab +2
Context Engineering: A Practitioner Methodology for Structured Human-AI Collaboration
Apr 5, 2026Elias CalboreanuContext Engineering LLM Context Management
Swift North AI Lab, The Swift Group, LLC, Maryland, USA.
ContextBudget: Budget-Aware Context Management for Long-Horizon Search Agents
Apr 2, 2026Yong Wu, YanZhao Zheng, TianZe Xu +9LLM Context Management Long-Horizon LLM Agents
Zhejiang University, Hangzhou, China · Alibaba Group, Hangzhou, China
Reasoning Shift: How Context Silently Shortens LLM Reasoning
Apr 1, 2026Gleb Rodionov, Roman Garipov, George YakushevLanguage Model Robustness LLM Context Management
Yandex · HSE University
View-oriented Conversation Compiler for Agent Trace Analysis
Mar 31, 2026Lvmin Zhang, Maneesh AgrawalaLLM Context Management Reasoning Trace Analysis
Stanford University
Developing Adaptive Context Compression Techniques for Large Language Models (LLMs) in Long-Running Interactions
Mar 31, 2026Payal Fofadiya, Sunil TiwariLLM Context Compression LLM Context Management
LinkedIn · eBay
Privacy Guard & Token Parsimony by Prompt and Context Handling and LLM Routing
Mar 30, 2026Alessio LangiuPrivacy Protection for LLM Agents Privacy Leakage in Language Models
National Research Council of Italy - Institute of Marine Sciences (CNR-ISMAR)
The Root Theorem of Context Engineering
Mar 29, 2026Borja Odriozola SchickContext Engineering LLM Context Management
Independent Researcher
Stream2LLM: Overlap Context Streaming and Prefill for Reduced Time-to-First-Token (TTFT)
Mar 29, 2026Rajveer Bachkaniwala, Chengqi Luo, Richard So +2LLM Inference LLM Inference Serving
Georgia Tech, Atlanta, USA
AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents
Mar 29, 2026Zhaopeng Feng, Liangcai Su, Zhen Zhang +16LLM Context Management Long-Horizon LLM Agents
Tongyi Lab, Alibaba Group
Conversation Tree Architecture: A Structured Framework for Context-Aware Multi-Branch LLM Conversations
Mar 22, 2026Pranav Hemanth, Sampriti SahaLLM Context Management
Pandemonium Research
Context Cartography: Toward Structured Governance of Contextual Space in Large Language Model Systems
Mar 21, 2026Zihua Wu, Georg GartnerLLM Context Management LLM Memory
NVIDIA · Research Division Cartography, TU Wien
PoC: Performance-oriented Context Compression for Large Language Models via Performance Prediction
Mar 20, 2026Runsong Zhao, Shilei Liu, Jiwei Tang +8Language Model Performance Prediction LLM Context Compression
Northeastern University, China · Future Living Lab of Alibaba · Tsinghua University
UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference
Mar 19, 2026Lang Zhou, Shuxuan Li, Zhuohao Li +3Long-Context Inference LLM Context Management
School of Computer Science and Engineering, Sun Yat-sen University · Shenzhen Loop Area Institute · Southern University of Science and Technology
A Context Alignment Pre-processor for Enhancing the Coherence of Human-LLM Dialog
Mar 17, 2026Ding WeiLLM Context Management Human-AI Collaboration
College of Architecture, Nanjing Tech University
When the Loop Closes: Architectural Limits of In-Context Isolation, Metacognitive Co-option, and the Two-Target Design Problem in Human-LLM Systems
Mar 14, 2026Z. Cheng, N. SongLLM Context Management Human-in-the-Loop AI
Independent Researcher
StatePlane: A Cognitive State Plane for Long-Horizon AI Systems Under Bounded Context
Mar 13, 2026Sasank Annapureddy, John Mulcahy, Anjaneya Prasad ThamataniLLM Context Management Persistent Memory for Language Models
Context Engineering: From Prompts to Corporate Multi-Agent Architecture
Mar 10, 2026Vera V. VishnyakovaContext Engineering LLM Context Management
Director, Center for Transfer and Management of Socio-Economic Information, HSE University, Moscow
The Missing Memory Hierarchy: Demand Paging for LLM Context Windows
Mar 9, 2026Tony MasonLLM Context Management
University of British Columbia Canada · Georgia Institute of Technology USA
GraphBit: A Graph-based Agentic Framework for Non-Linear Agent Orchestration
Mar 8, 2026Yeahia Sarker, Md Rahmat Ullah, Musa Molla +1LLM Agent Orchestration Multi-Agent Orchestration
MTSU · InfinitiBit GmbH · Salesforce Research
Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
Mar 8, 2026Pengfei DuLLM Agent Memory Agent Memory Management
Hong Kong Research Institute of Technology, HongKong, China
Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces
Mar 5, 2026Karan Gupta, Pranav Vajreshwari, Yash Pandya +3RL for Tool Use Agentic RL
Microsoft Research
Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned
Mar 5, 2026Nghi D. Q. BuiAI Coding Agents Coding Agents
OpenDev
Stacked from One: Multi-Scale Self-Injection for Context Window Extension
Mar 5, 2026Wei Han, Pan Zhou, Soujanya Poria +1Long-Context Language Model Inference Long-Context Language Modeling
Singapore University of Technology and Design (SUTD), Singapore · Singapore Management University (SMU), Singapore · Nanyang Technological University (NTU), Singapore +1
Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory
Mar 4, 2026Zhenting Wang, Huancheng Chen, Jiayun Wang +1LLM Agent Memory Memory Management for LLM Agents
Center for Advanced AI, Accenture
ASTRA-bench: Evaluating Tool-Use Agent Reasoning and Action Planning with Personal User Context
Mar 2, 2026Zidi Xiu, David Q. Sun, Kevin Cheng +9Tool-Use Evaluation AI Agent Benchmarks
Apple
PARCER as an Operational Contract to Reduce Variance, Cost, and Risk in LLM Systems
Mar 1, 2026Elzo Brito dos Santos FilhoContext Engineering LLM Reliability
Do LLMs Benefit From Their Own Words?
Feb 27, 2026Jenny Y. Huang, Leshem Choshen, Wei Sun +5LLM Context Management Context Compression
Department of Electrical Engineering and Computer Science, MIT · MIT–IBM Watson AI Lab · IBM Research
Contextual Memory Virtualisation: DAG-Based State Management and Structurally Lossless Trimming for LLM Agents
Feb 25, 2026Cosmo SantoniLLM Context Management Agent Memory Management
Imperial College London

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

HYVE: Hybrid Views for LLM Context Engineering over Machine Data

Jian Tan, Fan Bu, Yuqing Gao, Dev Khanolkar+4

Cisco Systems, Inc., San Jose, California, USA

LLM Context Management LLM Inference Efficiency Context Compression

Open paper AskPDF arXiv

Machine data is central to observability and diagnosis in modern computing systems, appearing in logs, metrics, telemetry traces, and configuration snapshots. When provided to large language models (LLMs), this data typically arrives as a mixture of natural language and structured payloads such as JSON or Python/AST literals. Yet LLMs remain brittle on such inputs, particularly when they are long, deeply nested, and dominated by repetitive structure. We present HYVE (HYbrid ViEw), a framework for LLM context engineering for inputs containing large machine-data payloads, inspired by database management principles. HYVE surrounds model invocation with coordinated preprocessing and postprocessing, centered on a request-scoped datastore augmented with schema information. During preprocessing, HYVE detects repetitive structure in raw inputs, materializes it in the datastore, transforms it into hybrid columnar and row-oriented views, and selectively exposes only the most relevant representation to the LLM. During postprocessing, HYVE either returns the model output directly, queries the datastore to recover omitted information, or performs a bounded additional LLM call for SQL-augmented semantic synthesis. We evaluate HYVE on diverse real-world workloads spanning knowledge QA, chart generation, anomaly detection, and multi-step network troubleshooting. Across these benchmarks, HYVE reduces token usage by 50-90% while maintaining or improving output quality. On structured generation tasks, it improves chart-generation accuracy by up to 132% and reduces latency by up to 83%. Overall, HYVE offers a practical approximation to an effectively unbounded context window for prompts dominated by large machine-data payloads.