mlsanityData to 14 Oct 2026

EvoMem: Improving Multi-Agent Planning with Dual-Evolving Memory

arXiv 2511.01912 ↗First posted 1 Nov 2025cs.MA cs.AI cs.LGcited by 6

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

Abstract (arXiv)

Planning has been a cornerstone of artificial intelligence for solving complex problems, and recent progress in LLM-based multi-agent frameworks have begun to extend this capability. However, the role of human-like memory within these frameworks remains largely unexplored. Understanding how agents coordinate through memory is critical for natural language planning, where iterative reasoning, constraint tracking, and error correction drive the success. Inspired by working memory model in cognitive psychology, we present EvoMem, a multi-agent framework built on a dual-evolving memory mechanism. The framework consists of three agents (Constraint Extractor, Verifier, and Actor) and two memory modules: Constraint Memory (CMem), which evolves across queries by storing task-specific rules and constraints while remains fixed within a query, and Query-feedback Memory (QMem), which evolves within a query by accumulating feedback across iterations for solution refinement. Both memory modules are reset at the end of each query session. Evaluations on trip planning, meeting planning, and calendar scheduling show consistent performance improvements, highlighting the effectiveness of EvoMem. This success underscores the importance of memory in enhancing multi-agent planning.

Key facts. Cited by 6 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 32 of its 38 references that are in the map. First posted on arXiv 1 Nov 2025.

Builds on

32 of 38 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory28 Apr
  2. 2025A-MEM: Agentic Memory for LLM Agents17 Feb

Other references · 30

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  3. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  4. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 556
  5. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agentscited by 392
  6. 2024Agent Workflow Memorycited by 383
  7. 2022PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Changecited by 382
  8. 2023On the Planning Abilities of Large Language Models : A Critical Investigationcited by 312
  9. 2025The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexitycited by 302
  10. 2023PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimizationcited by 233
  11. 2024OS-Copilot: Towards Generalist Computer Agents with Self-Improvementcited by 205
  12. 2024LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworkscited by 179
18 more
  1. 2024NATURAL PLAN: Benchmarking LLMs on Natural Language Planningcited by 128
  2. 2023SCM: Enhancing Large Language Model with Self-Controlled Memory Frameworkcited by 98
  3. 2024AIOS: LLM Agent Operating Systemcited by 97
  4. 2024Planning In Natural Language Improves LLM Search For Code Generationcited by 83
  5. 2023Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memorycited by 64
  6. 2024KnowAgent: Knowledge-Augmented Planning for LLM-Based Agentscited by 61
  7. 2025Evolving Deeper LLM Thinkingcited by 58
  8. 2025SETS: Leveraging Self-Verification and Self-Correction for Improved Test-Time Scalingcited by 54
  9. 2024Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizingcited by 49
  10. 2023Memory Augmented Large Language Models are Computationally Universalcited by 47
  11. 2024Tool-Planner: Task Planning with Clusters across Multiple Toolscited by 33
  12. 2024Exploring and Benchmarking the Planning Capabilities of Large Language Modelscited by 19
  13. 2024RePrompt: Planning by Automatic Prompt Engineering for Large Language Models Agentscited by 16
  14. 2025PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solvingcited by 15
  15. 2024A Human-Like Reasoning Framework for Multi-Phases Planning Task with Large Language Modelscited by 12
  16. 2024Enhancing Long Context Performance in LLMs Through Inner Loop Query Mechanismcited by 4
  17. 2024Transformer verbatim in-context retrieval across time and scalecited by 4
  18. 2024Memory, Space, and Planning: Multiscale Predictive Representationscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 44
  2. 2026Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitationscited by 21
  3. 2026TodyComm: Task-Oriented Dynamic Communication for Multi-Round LLM-based Multi-Agent Systemcited by 5
  4. 2026EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scalescited by 4
  5. 2026Embodied Task Planning via Graph-Informed Action Generation with Large Language Modelscited by 2
  6. 2026EvoDiagram: Agentic Editable Diagram Creation via Design Expertise Evolutioncited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2026EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective
  2. 2026AdMem: Advanced Memory for Task-solving Agents
  3. 2026CHIME: Credit-Aware Hierarchical Memory Evolution for Long-Horizon Agentic Planning
  4. 2026Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
  5. 2026Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents
  6. 2025Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memory
  7. 2025Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
  8. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions