mlsanityData to 14 Oct 2026

ACM: Agentic Context Management for Long Horizon Tasks

arXiv 2607.23809 ↗First posted 26 Jul 2026cs.AIcited by 10

On the map: LLM agents and tool use → Agent memory systems

Abstract (arXiv)

Agentic tasks are inherently long-horizon and multi-turn, constantly accumulating context through interactions with the environment. Existing context compression methods inevitably incur information loss and are triggered by rigid heuristic rules, leaving them misaligned with the agent's evolving reasoning focus. We propose Agentic Context Management (ACM), a framework that equips agents with purpose-built context editing tools for lossless context management. Inspired by the interaction between short-term and long-term human memory, the agent autonomously decides when to compress its context, offloads discarded content to an external memory system, and queries it on demand for later retrieval. Building on this framework, we further develop a post-training pipeline that constructs high-quality demonstrations of context management and improves model performance on both agentic search and coding tasks. Further analysis reveals that effective context management reduces peak token pressure, enables extended explorations, and yields more consistent solutions across independent trials. Code, data, and model checkpoints are available at https://github.com/lixiaochuan2020/agentic-context-management.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 29 of its 126 references that are in the map. First posted on arXiv 26 Jul 2026.

Builds on

29 of 126 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Scaling Long-Horizon LLM Agent via Context-Folding13 Oct
  2. 2025ACON: Optimizing Context Compression for Long-horizon LLM Agents1 Oct
  3. 2025MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents18 Jun
  4. 2025A-MEM: Agentic Memory for LLM Agents17 Feb

Other references · 25

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  4. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  5. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  6. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
  7. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  8. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  9. 2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,417
  10. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,402
  11. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  12. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,346
13 more
  1. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,336
  2. 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,195
  3. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 991
  4. 2024Training Software Engineering Agents and Verifiers with SWE-Gymcited by 336
  5. 2024TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Taskscited by 326
  6. 2024Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programscited by 291
  7. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 249
  8. 2025MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agentcited by 246
  9. 2025BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agentcited by 200
  10. 2025Dynamic Cheatsheet: Test-Time Learning with Adaptive Memorycited by 163
  11. 2025Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Managementcited by 51
  12. 2026DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agentscited by 50
  13. 2026SideQuest: Model-Driven KV Cache Management for Long-Horizon Agentic Reasoningcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 10.

10 papers.

  1. 2026Memory Control Signals Emerge Before Action in Long Horizon Agentscited by 1
  2. 2026StateComp: Learning When to Compress History in Long Horizon Agentscited by 1
  3. 2026Context Language Modelscited by 1
  4. 2026DRSR: Learning Set-Level Deletion Risk for Efficient Long-Horizon Agentscited by 0
  5. 2026Stable Geometry with Divergent Task Evidence for Efficient Long-Horizon Agent Compressioncited by 0
  6. 2026When Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compressioncited by 0
  7. 2026Coding Agent Memory Post-training: Unlocking the Memory Potential of Pre-trained File Operations for Long-Horizon Tasks via Reinforcement Learningcited by 0
  8. 2026Beyond Skill Evolution: Self-Evolving Context Management Policies for Long-Horizon Agent Harnessescited by 0
  9. 2026Harness-Search: Guiding Long-Horizon Search through Multi-Agent Coordinationcited by 0
  10. 2026Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practicecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL
  2. 2026Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability
  3. 2026CoMem: Context Management with A Decoupled Long-Context Model
  4. 2026Beyond Compaction: Structured Context Eviction for Long-Horizon Agents
  5. 2026FOCUS: Training-Free Decision-Preserving Context Compression for LLM Agents
  6. 2026AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications
  7. 2026ContextBudget: Budget-Aware Context Management for Long-Horizon Search Agents
  8. 2026Learning Agent-Compatible Context Management for Long-Horizon Tasks