mlsanityData to 7 Oct 2026

MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent

arXiv 2507.02259 ↗First posted 3 Jul 2025cs.CL cs.AI cs.LGcited by 235

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

Despite improvements by length extrapolation, efficient attention and memory modules, handling infinitely long documents with linear complexity without performance degradation during extrapolation remains the ultimate challenge in long-text processing. We directly optimize for long-text tasks in an end-to-end fashion and introduce a novel agent workflow, MemAgent, which reads text in segments and updates the memory using an overwrite strategy. We extend the DAPO algorithm to facilitate training via independent-context multi-conversation generation. MemAgent has demonstrated superb long-context capabilities, being able to extrapolate from an 8K context trained on 32K text to a 3.5M QA task with performance loss < 5% and achieves 95%+ in 512K RULER test.

Key facts. Cited by 235 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 63 of its 74 references that are in the map. First posted on arXiv 3 Jul 2025.

Builds on

63 of 74 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents18 Jun

Other references · 62

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  4. 2024Qwen2.5 Technical Reportcited by 4,713
  5. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  6. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  7. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  8. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  9. 2020Longformer: The Long-Document Transformercited by 3,362
  10. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  11. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  12. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,424
38 more
  1. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,115
  2. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 1,980
  3. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 1,979
  4. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  5. 2019Generating Long Sequences with Sparse Transformerscited by 1,523
  6. 2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,378
  7. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  8. 2025Understanding R1-Zero-Like Training: A Critical Perspectivecited by 1,276
  9. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,270
  10. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  11. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,193
  12. 2024DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Modelcited by 1,093
  13. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 893
  14. 2023RWKV: Reinventing RNNs for the Transformer Eracited by 814
  15. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 722
  16. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 721
  17. 2014Neural Turing Machinescited by 630
  18. 2017The NarrativeQA Reading Comprehension Challengecited by 590
  19. 2023YaRN: Efficient Context Window Extension of Large Language Modelscited by 584
  20. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
  21. 2021A Dataset of Information-Seeking Questions and Answers Anchored in Research Paperscited by 475
  22. 2025Group-in-Group Policy Optimization for LLM Agent Trainingcited by 442
  23. 2025Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attentioncited by 391
  24. 2021QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarizationcited by 363
  25. 2025RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learningcited by 357
  26. 2014Memory Networkscited by 354
  27. 2021Efficient Attentions for Long Document Summarizationcited by 342
  28. 2024Titans: Learning to Memorize at Test Timecited by 303
  29. 2023Effective Long-Context Scaling of Foundation Modelscited by 301
  30. 2023LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Modelscited by 279
  31. 2024Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Modelscited by 232
  32. 2025MoBA: Mixture of Block Attention for Long-Context LLMscited by 188
  33. 2023Compressing Context to Enhance Inference Efficiency of Large Language Modelscited by 185
  34. 2025Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learningcited by 159
  35. 2025Qwen2.5-1M Technical Reportcited by 158
  36. 2025MiniMax-01: Scaling Foundation Models with Lightning Attentioncited by 157
  37. 2023Scaling Laws of RoPE-based Extrapolationcited by 124
  38. 2024HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughlycited by 119

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 48; 2026: 187.

235 papers.

Sort:

By area:

  1. 2025Memory in the Age of AI Agentscited by 285
  2. 2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memorycited by 253
  3. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactionscited by 236
  4. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 195
  5. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 175
  6. 2025Scaling Long-Horizon LLM Agent via Context-Foldingcited by 136
  7. 2025ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarizationcited by 132
  8. 2025Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memorycited by 129
  9. 2026MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agentscited by 129
  10. 2025ACON: Optimizing Context Compression for Long-horizon LLM Agentscited by 126
  11. 2025MemGen: Weaving Generative Latent Memory for Self-Evolving Agentscited by 99
  12. 2025AgentFold: Long-Horizon Web Agents with Proactive Context Managementcited by 95
38 more
  1. 2025Recursive Language Modelscited by 94
  2. 2025Memp: Exploring Agent Procedural Memorycited by 88
  3. 2025PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memorycited by 82
  4. 2025Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoningcited by 68
  5. 2025Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Taskscited by 62
  6. 2025WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learningcited by 59
  7. 2025Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Managementcited by 51
  8. 2025Mem-α: Learning Memory Construction via Reinforcement Learningcited by 49
  9. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  10. 2026AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applicationscited by 46
  11. 2026SkillOS: Learning Skill Curation for Self-Evolving Agentscited by 45
  12. 2025SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agentcited by 44
  13. 2025General Agentic Memory Via Deep Researchcited by 42
  14. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 40
  15. 2025Agentic Entropy-Balanced Policy Optimizationcited by 39
  16. 2026CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discoverycited by 38
  17. 2025Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agentscited by 37
  18. 2026Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Taskscited by 37
  19. 2025Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecyclecited by 34
  20. 2026Dynamic Dual-Granularity Skill Bank for Agentic RLcited by 33
  21. 2025MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learningcited by 26
  22. 2025Accumulating Context Changes the Beliefs of Language Modelscited by 25
  23. 2026Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learningcited by 23
  24. 2025IterResearch: Rethinking Long-Horizon Agents with Interaction Scalingcited by 22
  25. 2026AgentOCR: Reimagining Agent History via Optical Self-Compressioncited by 22
  26. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applicationscited by 22
  27. 2026Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitationscited by 20
  28. 2026Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneouslycited by 19
  29. 2026Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generationcited by 18
  30. 2025Sculptor: Empowering LLMs with Cognitive Agency via Active Context Managementcited by 17
  31. 2025Learning Hierarchical Procedural Memory for LLM Agents through Bayesian Selection and Contrastive Refinementcited by 17
  32. 2025From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memorycited by 16
  33. 2026PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Recordscited by 16
  34. 2026Governing Evolving Memory in LLM Agents: Risks, Mechanisms, and the Stability and Safety Governed Memory (SSGM) Frameworkcited by 16
  35. 2026MEMENTO: Teaching LLMs to Manage Their Own Contextcited by 16
  36. 2025WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidancecited by 15
  37. 2026MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoningcited by 15
  38. 2026In-Place Test-Time Trainingcited by 15

50 most cited of 235 All 235 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026MemFit: Efficient Long-Term Agentic Memory
  2. 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
  3. 2026Mem++: Non-Destructive Memory for Long-Term Organizational LLM Agents
  4. 2025MemInsight: Autonomous Memory Augmentation for LLM Agents
  5. 2026MEMAUDIT: An Exact Package-Oracle Evaluation Protocol for Budgeted Long-Term LLM Memory Writing
  6. 2024MemLong: Memory-Augmented Retrieval for Long Text Modeling
  7. 2026Coding Agents are Effective Long-Context Processors
  8. 2026MemRefine: LLM-Guided Compression for Long-Term Agent Memory