mlsanityData to 7 Oct 2026

Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents

arXiv 2601.01885 ↗First posted 5 Jan 2026cs.CLcited by 72

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

Abstract (arXiv)

Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows, making effective memory management critical. Existing methods typically handle long-term memory (LTM) and short-term memory (STM) as separate components, relying on heuristics or auxiliary controllers, which limits adaptability and end-to-end optimization. In this paper, we propose Agentic Memory (AgeMem), a unified framework that integrates LTM and STM management directly into the agent's policy. AgeMem exposes memory operations as tool-based actions, enabling the LLM agent to autonomously decide what and when to store, retrieve, update, summarize, or discard information. To train such unified behaviors, we propose a three-stage progressive reinforcement learning strategy and design a step-wise GRPO to address sparse and discontinuous rewards induced by memory operations. Experiments on five long-horizon benchmarks demonstrate that AgeMem consistently outperforms strong memory-augmented baselines across multiple LLM backbones, achieving improved task performance, higher-quality long-term memory, and more efficient context usage.

Key facts. Cited by 72 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 29 of its 67 references that are in the map. First posted on arXiv 5 Jan 2026.

Builds on

29 of 67 references.

Closest ancestors · 11

Same direction, newest first

  1. 2025Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks14 Oct
  2. 2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning27 Aug
  3. 2025MIRIX: Multi-Agent Memory System for LLM-Based Agents10 Jul
  4. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions7 Jul
  5. 2025How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior21 May
  6. 2025MemInsight: Autonomous Memory Augmentation for LLM Agents27 Mar
  7. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  8. 2025Zep: A Temporal Knowledge Graph Architecture for Agent Memory20 Jan
  9. 2024Hello Again! LLM-powered Personalized Agent for Long-term Dialogue9 Jun
  10. 2024A Survey on the Memory Mechanism of Large Language Model based Agents21 Apr
  11. 2024RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents6 Feb

Other references · 18

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  3. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  4. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  5. 2025ToolRL: Reward is All Tool Learning Needscited by 342
  6. 2024AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agentscited by 319
  7. 2022ScienceWorld: Is your Agent Smarter than a 5th Grader?cited by 298
  8. 2018BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learningcited by 238
  9. 2025From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMscited by 119
  10. 2025A Survey on Code Generation with LLM-based Agentscited by 104
  11. 2025Inducing Programmatic Skills for Agentic Taskscited by 103
  12. 2025On Memory Construction and Retrieval for Personalized Conversational Agentscited by 101
6 more
  1. 2024RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMscited by 89
  2. 2024MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generationcited by 43
  3. 2024KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systemscited by 38
  4. 2024Long Term Memory: The Foundation of AI Self-Evolutioncited by 29
  5. 2024What Should We Engineer in Prompts? Training Humans in Requirement-Driven LLM Usecited by 24
  6. 2025The Effect of State Representation on LLM Agent Behavior in Dynamic Routing Gamescited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 72.

72 papers.

Sort:

By area:

  1. 2026Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontierscited by 60
  2. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  3. 2026Supersede: Diagnosing and Training the Memory-Update Gap in LLM Agentscited by 13
  4. 2026EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agentscited by 11
  5. 2026Graph-Native Cognitive Memory for AI Agents: Formal Belief Revision Semantics for Versioned Memory Architecturescited by 9
  6. 2026Belief Memory: Agent Memory Under Partial Observabilitycited by 9
  7. 2026MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agentscited by 9
  8. 2026Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baselinecited by 8
  9. 2026Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memorycited by 8
  10. 2026SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directionscited by 7
  11. 2026Retrieval-Augmented LLM Agents: Learning to Learn from Experiencecited by 6
  12. 2026Memory Intelligence Agentcited by 6
38 more
  1. 2026Toward a Theory of Hierarchical Memory for Language Agentscited by 5
  2. 2026Co-Evolving Skill Generation and Policy Optimizationcited by 5
  3. 2026RaMem: Contextual Reinstatement for Long-term Agentic Memorycited by 5
  4. 2026TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memorycited by 5
  5. 2026AdaMEM: Test-Time Adaptive Memory for Language Agentscited by 4
  6. 2026AutoMem: Automated Learning of Memory as a Cognitive Skillcited by 4
  7. 2026GAAMA: Graph Augmented Associative Memory for Agentscited by 3
  8. 2026GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learningcited by 3
  9. 2026Learning When to Remember: Risk-Sensitive Contextual Bandits for Abstention-Aware Memory Retrieval in LLM-Based Coding Agentscited by 3
  10. 2026MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agentscited by 3
  11. 2026Mem-π: Adaptive Memory through Learning When and What to Generatecited by 3
  12. 2026Not All Skills Help: Measuring and Repairing Agent Knowledgecited by 3
  13. 2026DynamicMem: A Long-Horizon Memory Benchmark in Real-World Settingscited by 3
  14. 2026LLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via State Proprioceptioncited by 3
  15. 2026Procedural Memory Distillation: Online Reflection for Self-Improving Language Modelscited by 3
  16. 2026Memory Reward Inflation in Self-Improving LLM Agentscited by 3
  17. 2026Neuromem: A Granular Decomposition of the Streaming Lifecycle in External Memory for LLMscited by 2
  18. 2026Synergy: A Next-Generation General-Purpose Agent for Open Agentic Webcited by 2
  19. 2026What Happens Inside Agent Memory? Circuit Analysis from Emergence to Diagnosiscited by 2
  20. 2026PRISM: Pareto-Efficient Retrieval over Intent-Aware Structured Memory for Long-Horizon Agentscited by 2
  21. 2026R^2-Mem: Reflective Experience for Memory Searchcited by 2
  22. 2026DimMem: Dimensional Structuring for Efficient Long-Term Agent Memorycited by 2
  23. 2026From Passive Retrieval to Active Memory Navigation: Learning to Use Memory as a Structured Action Spacecited by 2
  24. 2026Verifiable Memory: Learning Unified Memory Management with Local and Global Verifiers for Large Language Model Agentscited by 2
  25. 2026EffGen: Enabling Small Language Models as Capable Autonomous Agentscited by 1
  26. 2026The Missing Knowledge Layer in Cognitive Architectures for AI Agentscited by 1
  27. 2026StatefulDiscovery: Evidence-Calibrated Claim Formation in Open-Ended Scientific Discoverycited by 1
  28. 2026The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomycited by 1
  29. 2026Speculate with Memory: Lossless Acceleration for LLM Agentscited by 1
  30. 2026SF-AMS: Strategic Forgetting for Structured Memory in LLM Agentcited by 1
  31. 2026Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agentscited by 1
  32. 2026Agents in the Large: Perception-Centered Architecture for Persistent Agentscited by 1
  33. 2026Rollback the World, Keep the Reflection: Rollback-Induced Reflection for Long-Horizon LLM Agentscited by 1
  34. 2026RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agentscited by 1
  35. 2026Shifting Adaptation from Weight Space to Memory Space: A Memory-Augmented Agent for Medical Image Segmentationcited by 0
  36. 2026Personalizing Embodied Multimodal Large Language Model Agents over Long-term User Interactionscited by 0
  37. 2026Rosetta Memory: Adaptive Memory for Cross-LLM Agentscited by 0
  38. 2026Toward Self-Evolution-Ready Workflow Harnesses: A Reversible Migration Path and Convertibility Taxonomy for Expert LLM Pipelinescited by 0

50 most cited of 72 All 72 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026AdMem: Advanced Memory for Task-solving Agents
  2. 2026Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
  3. 2026Choosing How to Remember: Adaptive Memory Structures for LLM Agents
  4. 2025Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics
  5. 2026Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents
  6. 2026DeltaMem: Towards Agentic Memory Management via Reinforcement Learning
  7. 2025Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
  8. 2026LatentMem: Customizing Latent Memory for Multi-Agent Systems