mlsanityData to 7 Oct 2026

Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving

arXiv 2507.06229 ↗First posted 8 Jul 2025cs.CL cs.AIcited by 90

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

Abstract (arXiv)

AI agent frameworks operate in isolation, forcing agents to rediscover solutions and repeat mistakes across different systems. Despite valuable problem-solving experiences accumulated by frameworks like smolagents, OpenHands, and OWL, this knowledge remains trapped within individual systems, preventing the emergence of collective intelligence. Current memory systems focus on individual agents or framework-specific demonstrations, failing to enable cross-architecture knowledge transfer. We introduce AGENT KB, a universal memory infrastructure enabling seamless experience sharing across heterogeneous agent frameworks without retraining. AGENT KB aggregates trajectories into a structured knowledge base and serves lightweight APIs. At inference time, hybrid retrieval operates through two stages: planning seeds agents with cross-domain workflows, while feedback applies targeted diagnostic fixes. A disagreement gate ensures retrieved knowledge enhances rather than disrupts reasoning, addressing knowledge interference in cross-framework transfer. We validate AGENT KB across major frameworks on GAIA, Humanity's Last Exam, GPQA, and SWE-bench. Results show substantial improvements across diverse model families: compared to baseline pass@1, smolagents with AGENT KB achieve up to 18.7pp gains at pass@3 (55.2% -> 73.9%), while OpenHands improves 4.0pp on SWE-bench pass@1 (24.3% -> 28.3%). Similar improvements are observed across all base model families. Ablations confirm that hybrid retrieval and feedback stages are essential, with automatically generated experiences matching manual curation. This establishes the foundation for collective agent intelligence through shared memory infrastructures.

Key facts. Cited by 90 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 67 of its 80 references that are in the map. First posted on arXiv 8 Jul 2025.

Builds on

67 of 80 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025Task Memory Engine (TME): Enhancing State Awareness for Multi-Step LLM Agent Tasks11 Apr
  2. 2025MemInsight: Autonomous Memory Augmentation for LLM Agents27 Mar
  3. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  4. 2025Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents10 Feb
  5. 2025Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalization3 Feb
  6. 2024On the Structural Memory of LLM Agents17 Dec
  7. 2024HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model18 Aug
  8. 2024AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents5 Jul
  9. 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts15 Feb

Other references · 58

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  3. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  4. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  5. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  6. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,628
  7. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  8. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  9. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
  10. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 752
  11. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 724
  12. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
38 more
  1. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 616
  2. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
  3. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Modelscited by 423
  4. 2023RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generationcited by 357
  5. 2024Agent Workflow Memorycited by 342
  6. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capabilitycited by 320
  7. 2024Training Software Engineering Agents and Verifiers with SWE-Gymcited by 300
  8. 2024Magentic-One: A Generalist Multi-Agent System for Solving Complex Taskscited by 221
  9. 2024OS-Copilot: Towards Generalist Computer Agents with Self-Improvementcited by 203
  10. 2023Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Controlcited by 180
  11. 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Societycited by 180
  12. 2025WebWalker: Benchmarking LLMs in Web Traversalcited by 171
  13. 2025OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automationcited by 129
  14. 2025Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Taskscited by 128
  15. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  16. 2025From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMscited by 119
  17. 2023Agents: An Open-source Framework for Autonomous Language Agentscited by 116
  18. 2025Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolutioncited by 114
  19. 2024Symbolic Learning Enables Self-Evolving Agentscited by 104
  20. 2023MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversationcited by 94
  21. 2025Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environmentscited by 93
  22. 2024MEMORYLLM: Towards Self-Updatable Large Language Modelscited by 89
  23. 2024Agent Planning with World Knowledge Modelcited by 66
  24. 2024KnowAgent: Knowledge-Augmented Planning for LLM-Based Agentscited by 61
  25. 2024Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answeringcited by 59
  26. 2025AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agentscited by 49
  27. 2023EcoAssistant: Using LLM Assistant More Affordably and Accuratelycited by 47
  28. 2025SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?cited by 45
  29. 2025OAgents: An Empirical Study of Building Effective Agentscited by 28
  30. 2025HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generationcited by 24
  31. 2024TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned Decisioncited by 23
  32. 2025SEW: Self-Evolving Agentic Workflows for Automated Code Generationcited by 18
  33. 2024Mitigating Hallucinations in Large Language Models via Self-Refinement-Enhanced Knowledge Retrievalcited by 16
  34. 2025LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household Roboticscited by 15
  35. 2024Class-Level Code Generation from Natural Language Using Iterative, Tool-Enhanced Reasoning over Repositorycited by 14
  36. 2025AI-native Memory 2.0: Second Mecited by 14
  37. 2024Towards LifeSpan Cognitive Systemscited by 13
  38. 2025Review of Case-Based Reasoning for LLM Agents: Theoretical Foundations, Architectural Components, and Cognitive Integrationcited by 12

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 26; 2026: 64.

90 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. 2026SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learningcited by 252
  4. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 175
  5. 2026SimpleMem: Efficient Lifelong Memory for LLM Agentscited by 140
  6. 2025Scaling Long-Horizon LLM Agent via Context-Foldingcited by 136
  7. 2025Memento: Fine-tuning LLM Agents without Fine-tuning LLMscited by 119
  8. 2025WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agentcited by 114
  9. 2025Memp: Exploring Agent Procedural Memorycited by 88
  10. 2026SkillClaw: Let Skills Evolve Collectively with Agentic Evolvercited by 76
  11. 2026XSkill: Continual Learning from Experience and Skills in Multimodal Agentscited by 71
  12. 2026SkillX: Automatically Constructing Skill Knowledge Bases for Agentscited by 69
38 more
  1. 2025Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoningcited by 68
  2. 2025SWE-Exp: Experience-Driven Software Issue Resolutioncited by 64
  3. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 58
  4. 2025Training-Free Group Relative Policy Optimizationcited by 53
  5. 2025FLEX: Continuous Agent Evolution via Forward Learning from Experiencecited by 51
  6. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  7. 2026SkillOS: Learning Skill Curation for Self-Evolving Agentscited by 45
  8. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 40
  9. 2026MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wildcited by 35
  10. 2025Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Executioncited by 27
  11. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applicationscited by 22
  12. 2026From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flawscited by 21
  13. 2026From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanismscited by 19
  14. 2025WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidancecited by 15
  15. 2026SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphscited by 15
  16. 2025Towards Personalized Deep Research: Benchmarks and Evaluationscited by 14
  17. 2026EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspectivecited by 14
  18. 2025GUI-ReWalk: Massive Data Generation for GUI Agent via Stochastic Exploration and Intent-Aware Reasoningcited by 12
  19. 2025AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agentscited by 12
  20. 2026LatentMem: Customizing Latent Memory for Multi-Agent Systemscited by 12
  21. 2025How Far Are We from Genuinely Useful Deep Research Agents?cited by 11
  22. 2026Toward Efficient Agents: Memory, Tool learning, and Planningcited by 11
  23. 2026ClawArena: Benchmarking AI Agents in Evolving Information Environmentscited by 10
  24. 2025LatentEvolve: Self-Evolving Test-Time Scaling in Latent Spacecited by 8
  25. 2025MemWeaver: A Hierarchical Memory from Textual Interactive Behaviors for Personalized Generationcited by 8
  26. 2026Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Applicationcited by 8
  27. 2026SEAGym: An Evaluation Environment for Self-Evolving LLM Agentscited by 8
  28. 2026TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarkingcited by 7
  29. 2025A2FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoningcited by 6
  30. 2025Agentic Software Issue Resolution with Large Language Models: A Surveycited by 6
  31. 2026PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planningcited by 6
  32. 2026SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agentscited by 6
  33. 2025CRMWeaver: Building Powerful Business Agent via Agentic RL and Shared Memoriescited by 5
  34. 2026Aligning Agentic World Models via Knowledgeable Experience Learningcited by 5
  35. 2026Co-Evolving Skill Generation and Policy Optimizationcited by 5
  36. 2026Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalizationcited by 4
  37. 2026AdaMEM: Test-Time Adaptive Memory for Language Agentscited by 4
  38. 2026From Atom to Community: Structured and Evolving Agent Memory for User Behavior Modelingcited by 3

50 most cited of 90 All 90 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Multi-Agent Transactive Memory
  2. 2026MemCollab: Cross-Model Memory Collaboration via Contrastive Trajectory Distillation
  3. 2026Learning to Share: Selective Memory for Efficient Parallel Agentic Systems
  4. 2026Distilling Agentic Systems: A Roadmap across Models, Artifacts, and Harnesses
  5. 2025Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
  6. 2025Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memory
  7. 2026Memory as Middleware for Self-Improving AI Agents
  8. 2025Decentralizing AI Memory: SHIMI, a Semantic Hierarchical Memory Index for Scalable Agent Reasoning