mlsanityData to 7 Oct 2026

ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization

arXiv 2509.13313 ↗First posted 16 Sep 2025cs.CLcited by 132

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

Abstract (arXiv)

Large Language Model (LLM)-based web agents excel at knowledge-intensive tasks but face a fundamental conflict between the need for extensive exploration and the constraints of limited context windows. Current solutions typically rely on architectural modifications, e.g., internal memory tokens, which break compatibility with pre-existing agents and necessitate costly end-to-end retraining. To overcome these limitations, we introduce ReSum, a lightweight, plug-and-play paradigm that enables unbounded exploration by periodically invoking an external tool to condense interaction histories into compact summaries. Although this paradigm functions without training, standard agents are not inherently aligned to reason over such compressed contexts. To bridge this gap, we propose ReSum-GRPO, which adapts Group Relative Policy Optimization (GRPO) via advantage broadcasting to propagate final rewards across segmented trajectories, enabling credit assignments over long-horizons. Extensive experiments show that ReSum achieves a 4.5% improvement over ReAct in training-free settings, with ReSum-GRPO yielding a further 8.2% gain. Notably, with only 1K training samples, a ReSum-enhanced 30B agent achieves competitive performance with leading open-source models, showing ReSum's effectiveness.

Key facts. Cited by 132 papers in the map (data through 7 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 30 of its 41 references that are in the map. First posted on arXiv 16 Sep 2025.

Builds on

30 of 41 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents18 Jun
  2. 2025A-MEM: Agentic Memory for LLM Agents17 Feb

Other references · 28

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2024Qwen2.5 Technical Reportcited by 4,713
  5. 2017Deep reinforcement learning from human preferencescited by 3,846
  6. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  7. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  8. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  9. 2024A Survey on LLM-as-a-Judgecited by 1,384
  10. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  11. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  12. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 616
16 more
  1. 2025UI-TARS: Pioneering Automated GUI Interaction with Native Agentscited by 584
  2. 2024LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methodscited by 451
  3. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Modelscited by 423
  4. 2024Measuring short-form factuality in large language modelscited by 345
  5. 2025MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agentcited by 235
  6. 2025WebSailor: Navigating Super-human Reasoning for Web Agentcited by 218
  7. 2025WebDancer: Towards Autonomous Information Seeking Agencycited by 180
  8. 2025WebWalker: Benchmarking LLMs in Web Traversalcited by 171
  9. 2025Agentic Reinforced Policy Optimizationcited by 166
  10. 2025Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RLcited by 144
  11. 2025BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinesecited by 139
  12. 2025MemOS: A Memory OS for AI Systemcited by 129
  13. 2025WebShaper: Agentically Data Synthesizing via Information-Seeking Formalizationcited by 118
  14. 2024Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigationcited by 116
  15. 2025WebExplorer: Explore and Evolve for Training Long-Horizon Web Agentscited by 86
  16. 2025Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RLcited by 75

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 19; 2026: 113.

132 papers.

Sort:

By area:

  1. 2026Kimi K2.5: Visual Agentic Intelligencecited by 449
  2. 2025Memory in the Age of AI Agentscited by 285
  3. 2025Scaling Long-Horizon LLM Agent via Context-Foldingcited by 136
  4. 2025ACON: Optimizing Context Compression for Long-horizon LLM Agentscited by 126
  5. 2025Recursive Language Modelscited by 94
  6. 2025Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Taskscited by 62
  7. 2025Tongyi DeepResearch Technical Reportcited by 53
  8. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 40
  9. 2025Agentic Entropy-Balanced Policy Optimizationcited by 39
  10. 2026LongCat-Flash-Thinking-2601 Technical Reportcited by 32
  11. 2025A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applicationscited by 21
  12. 2025Rethinking Thinking Tokens: LLMs as Improvement Operatorscited by 20
38 more
  1. 2026Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Taskscited by 18
  2. 2025Context Engineering 2.0: The Context of Context Engineeringcited by 17
  3. 2026MEMENTO: Teaching LLMs to Manage Their Own Contextcited by 16
  4. 2026Mem-T: Densifying Rewards for Long-Horizon Memory Agentscited by 14
  5. 2026ContextBudget: Budget-Aware Context Management for Long-Horizon Search Agentscited by 13
  6. 2025AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agentscited by 12
  7. 2026MemoBrain: Executive Memory as an Agentic Brain for Reasoningcited by 12
  8. 2026Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Designcited by 12
  9. 2026SWE-MeM: Learning Adaptive Memory Management for Long-Horizon Coding Agentscited by 12
  10. 2025Lost in the Maze: Overcoming Context Limitations in Long-Horizon Agentic Searchcited by 11
  11. 2026Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memorycited by 11
  12. 2026Synthetic Sandbox for Training Machine Learning Engineering Agentscited by 11
  13. 2026VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactionscited by 11
  14. 2026Self-Compacting Language Model Agentscited by 11
  15. 2025Repurposing Synthetic Data for Fine-grained Search Agent Supervisioncited by 10
  16. 2026SAM: State-Adaptive Memory for Long-Horizon Reasoning Agentcited by 10
  17. 2026JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolutioncited by 10
  18. 2026Do Not Waste Your Rollouts: Recycling Search Experience for Efficient Test-Time Scalingcited by 9
  19. 2026RE-TRAC: REcursive TRAjectory Compression for Deep Search Agentscited by 9
  20. 2026Towards Long-horizon Agentic Multimodal Searchcited by 9
  21. 2025Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AIcited by 8
  22. 2026QUEST: Training Frontier Deep Research Agents with Fully Synthetic Taskscited by 8
  23. 2026CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agentscited by 8
  24. 2026WebAnchor: Anchoring Agent Planning to Stabilize Long-Horizon Web Reasoningcited by 7
  25. 2026Analyzing Reasoning Consistency in Large Multimodal Models under Cross-Modal Conflictscited by 7
  26. 2026U-Fold: Dynamic Intent-Aware Context Folding for User-Centric Agentscited by 7
  27. 2026Beyond Compaction: Structured Context Eviction for Long-Horizon Agentscited by 7
  28. 2025FoldAct: Efficient and Stable Context Folding for Long-Horizon Search Agentscited by 6
  29. 2026ARC: Active and Reflection-driven Context Management for Long-Horizon Information Seeking Agentscited by 6
  30. 2026RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimizationcited by 6
  31. 2026Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipecited by 6
  32. 2026Autonomous Research Agents: A Survey of AI Scientists and the Verification Gapcited by 6
  33. 2025Nested Browser-Use Learning for Agentic Information Seekingcited by 5
  34. 2026Agent-Omit: Adaptive Context Omission for Efficient LLM Agentscited by 5
  35. 2026VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graphcited by 5
  36. 2026Slipstream: Trajectory-Grounded Compaction Validation for Long-Horizon Agentscited by 5
  37. 2026CoMem: Context Management with A Decoupled Long-Context Modelcited by 5
  38. 2026Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instabilitycited by 5

50 most cited of 132 All 132 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents
  2. 2026WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search
  3. 2025AgentFold: Long-Horizon Web Agents with Proactive Context Management
  4. 2026M2: Dual-Memory Augmentation for Long-Horizon Web Agents via Trajectory Summarization and Insight Retrieval
  5. 2026Learning Agent-Compatible Context Management for Long-Horizon Tasks
  6. 2026ContextWeaver: Selective and Dependency-Structured Memory Construction for LLM Agents
  7. 2026LexiHorizon: Stabilizing Reinforcement Learning for Long-Horizon Deep Search
  8. 2026SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration