mlsanityData to 7 Oct 2026

MemPO: Self-Memory Policy Optimization for Long-Horizon Agents

arXiv 2603.00680 ↗First posted 28 Feb 2026cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

Long-horizon agents face the challenge of growing context size during interaction with environment, which degrades the performance and stability. Existing methods typically introduce the external memory module and look up the relevant information from the stored memory, which prevents the model itself from proactively managing its memory content and aligning with the agent's overarching task objectives. To address these limitations, we propose the self-memory policy optimization algorithm (MemPO), which enables the agent (policy model) to autonomously summarize and manage their memory during interaction with environment. By improving the credit assignment mechanism based on memory effectiveness, the policy model can selectively retain crucial information, significantly reducing token consumption while preserving task performance. Extensive experiments and analyses confirm that MemPO achieves absolute F1 score gains of 25.98 over the base model and 7.1 over the previous SOTA baseline, while reducing token usage by 67.58% and 73.12%. The code is released at https://github.com/TheNewBeeKing/MemPO.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 30 of its 41 references that are in the map. First posted on arXiv 28 Feb 2026.

Builds on

30 of 41 references.

References · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  6. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  7. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  8. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  9. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  10. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  11. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  12. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
18 more
  1. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  2. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,000
  3. 2024CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challengescited by 278
  4. 2025MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agentscited by 226
  5. 2024Data Interpreter: An LLM Agent For Data Sciencecited by 222
  6. 2023Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Controlcited by 180
  7. 2024MapCoder: Multi-Agent Code Generation for Competitive Problem Solvingcited by 177
  8. 2025WebWalker: Benchmarking LLMs in Web Traversalcited by 171
  9. 2024Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generationcited by 158
  10. 2024VerilogCoder: Autonomous Verilog Coding Agents with Graph-based Planning and Abstract Syntax Tree (AST)-based Waveform Tracing Toolcited by 85
  11. 2025Deep Research: A Survey of Autonomous Research Agentscited by 63
  12. 2026ExpSeek: Self-Triggered Experience Seeking for Web Agentscited by 23
  13. 2025Beyond Turn Limits: Training Deep Search Agents with Dynamic Context Windowcited by 19
  14. 2024RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generationcited by 10
  15. 2024Exploring Forgetting in Large Language Model Pre-Trainingcited by 9
  16. 2026ATTNPO: Attention-Guided Process Supervision for Efficient Reasoningcited by 9
  17. 2025MOA: Multi-Objective Alignment for Role-Playing Agentscited by 5
  18. 2025Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraintscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 11.

11 papers.

  1. 2026Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agentscited by 16
  2. 2026HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agentscited by 4
  3. 2026ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RLcited by 3
  4. 2026The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agentscited by 1
  5. 2026Break It Down, Pass It On: Cross-Task Skill Transfer in LLM Agentscited by 1
  6. 2026MemOPD: On-Policy Distillation through Memory State Alignment for Long-Horizon Agentscited by 0
  7. 2026FORGE: Form-Optimal Routing of Grounded Evidence for Frozen LLM Agentscited by 0
  8. 2026Coding Agent Memory Post-training: Unlocking the Memory Potential of Pre-trained File Operations for Long-Horizon Tasks via Reinforcement Learningcited by 0
  9. 2026Beyond Skill Evolution: Self-Evolving Context Management Policies for Long-Horizon Agent Harnessescited by 0
  10. 2026Learning What to Remember: Long-horizon Counterfactual Memory Optimizationcited by 0
  11. 2026Causal Memory Policy: Making Memory Utility Identifiable by Intervening on Retrievalcited by 0