mlsanityData to 14 Oct 2026

EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents

arXiv 2605.13941 ↗First posted 13 May 2026cs.LG cs.AIcited by 15

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

also in 1 more
Abstract (arXiv)

Long-term memory is essential for LLM agents that operate across multiple sessions, yet existing memory systems treat retrieval infrastructure as fixed: stored content evolves while scoring functions, fusion strategies, and answer-generation policies remain frozen at deployment. We argue that truly adaptive memory requires co-evolution at two levels: the stored knowledge and the retrieval mechanism that queries it. We present EvolveMem, a self-evolving memory architecture that exposes its full retrieval configuration as a structured action space optimized by an LLM-powered diagnosis module. In each evolution round, the module reads per-question failure logs, identifies root causes, and proposes targeted configuration adjustments; a guarded meta-analyzer applies them with automatic revert-on-regression and explore-on-stagnation safeguards. This closed-loop self-evolution realizes an AutoResearch process: the system autonomously conducts iterative research cycles on its own architecture, replacing manual configuration tuning. Starting from a minimal baseline, the process converges autonomously, discovering effective retrieval strategies including entirely new configuration dimensions not present in the original action space. On LoCoMo, EvolveMem outperforms the strongest baseline by 25.7% relative and achieves a 78.0% relative improvement over the minimal baseline. On MemBench, EvolveMem exceeds the strongest baseline by 18.9% relative. Evolved configurations transfer across benchmarks with positive rather than catastrophic transfer, indicating that the self-evolution process captures universal retrieval principles rather than benchmark-specific heuristics. Code is available at https://github.com/aiming-lab/SimpleMem.

Key facts. Cited by 15 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 39 of its 42 references that are in the map. First posted on arXiv 13 May 2026.

Builds on

39 of 42 references.

Closest ancestors · 13

Same direction, newest first

  1. 2026MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents2 Feb
  2. 2026SimpleMem: Efficient Lifelong Memory for LLM Agents5 Jan
  3. 2026Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents5 Jan
  4. 2025MemEvolve: Meta-Evolution of Agent Memory Systems21 Dec
  5. 2025Memory in the Age of AI Agents15 Dec
  6. 2025Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory25 Nov
  7. 2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning27 Aug
  8. 2025MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents20 Jun
  9. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory28 Apr
  10. 2025In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents11 Mar
  11. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  12. 2024A Survey on the Memory Mechanism of Large Language Model based Agents21 Apr
1 more
  1. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb

Other references · 26

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  4. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  5. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  6. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  7. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  8. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  9. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 876
  10. 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Modelscited by 557
  11. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 556
  12. 2023Active Retrieval Augmented Generationcited by 516
14 more
  1. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  2. 2023Cognitive Architectures for Language Agentscited by 429
  3. 2026SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learningcited by 278
  4. 2024Corrective Retrieval Augmented Generationcited by 197
  5. 2023Augmenting Language Models with Long-Term Memorycited by 189
  6. 2025EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecyclecited by 137
  7. 2026MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memorycited by 129
  8. 2025On Memory Construction and Retrieval for Personalized Conversational Agentscited by 105
  9. 2023SCM: Enhancing Large Language Model with Self-Controlled Memory Frameworkcited by 98
  10. 2024MEMORYLLM: Towards Self-Updatable Large Language Modelscited by 93
  11. 2025MemVerse: Multimodal Memory for Lifelong Learning Agentscited by 35
  12. 2024λ-Tune: Harnessing Large Language Models for Automated Database System Tuningcited by 19
  13. 2026Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memorycited by 14
  14. 2025A New Paradigm in Tuning Learned Indexes: A Reinforcement Learning Enhanced Approachcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 15.

15 papers.

Sort:

By area:

  1. 2026RRSI: Regularized Recursive Self-Improvement of Agent Harnessescited by 13
  2. 2026Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnessescited by 9
  3. 2026AutoMem: Automated Learning of Memory as a Cognitive Skillcited by 5
  4. 2026Mi-Memory: A Lifecycle Memory Framework for Personal AIcited by 3
  5. 2026AdaMem: Learning What to Remember with Adaptive Memory Policies for Personalized Agentscited by 2
  6. 2026MemChain: Learning Interpretable Memory Traces for Memory-Augmented LLM Agentscited by 2
  7. 2026Workflow Closure Is Not Scientific Closure in Auto-Research Systemscited by 1
  8. 2026ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memorycited by 0
  9. 2026Rehearse: Stepping Back from the Confidence Cliff in Self-Improving Autoresearchcited by 0
  10. 2026Vestrum: Improving Agent Harnesses by Adapting Their Verification, Structure and Memorycited by 0
  11. 2026Remember Before You're Asked: MemDream for Self-Probing Memory Evolutioncited by 0
  12. 2026MemCodex: Self-Programming Hierarchical Memory for Language Agentscited by 0
3 more
  1. 2026Capability-Driven Self-Evolution of Agent Memorycited by 0
  2. 2026Recurrent Harness for Agentic Continual Learningcited by 0
  3. 2026Evolve Together, Fall into Place: How Social Scaffolding Shapes Self-Evolving Multi-Agent Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval
  2. 2026SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory
  3. 2026AMA: Adaptive Memory via Multi-Agent Collaboration
  4. 2026MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution
  5. 2025MemR3: Memory Retrieval via Reflective Reasoning for LLM Agents
  6. 2026Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agents
  7. 2026CoEvo-Mem: Co-Evolving Retrieval Policy and Memory Bank for LLM Agents
  8. 2026Chain-of-Memory: Lightweight Memory Construction with Dynamic Evolution for LLM Agents