mlsanityData to 7 Oct 2026

Agent Workflow Memory

arXiv 2409.07429 ↗First posted 11 Sep 2024cs.CLcited by 342

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

Despite the potential of language model-based agents to solve real-world tasks such as web navigation, current methods still struggle with long-horizon tasks with complex action trajectories. In contrast, humans can flexibly solve complex tasks by learning reusable task workflows from past experiences and using them to guide future actions. To build agents that can similarly benefit from this process, we introduce Agent Workflow Memory (AWM), a method for inducing commonly reused routines, i.e., workflows, and selectively providing workflows to the agent to guide subsequent generations. AWM flexibly applies to both offline and online scenarios, where agents induce workflows from training examples beforehand or from test queries on the fly. We experiment on two major web navigation benchmarks -- Mind2Web and WebArena -- that collectively cover 1000+ tasks from 200+ domains across travel, shopping, and social media, among others. AWM substantially improves the baseline results by 24.6% and 51.1% relative success rate on Mind2Web and WebArena while reducing the number of steps taken to solve WebArena tasks successfully. Furthermore, online AWM robustly generalizes in cross-task, website, and domain evaluations, surpassing baselines from 8.9 to 14.0 absolute points as train-test task distribution gaps widen.

Key facts. Cited by 342 papers in the map (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 25 of its 31 references that are in the map. First posted on arXiv 11 Sep 2024.

Builds on

25 of 31 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?22 Jul
  2. 2024WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?12 Mar
  3. 2023WebArena: A Realistic Web Environment for Building Autonomous Agents25 Jul
  4. 2023Mind2Web: Towards a Generalist Agent for the Web9 Jun
  5. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents4 Jul

Other references · 20

  1. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  2. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
  3. 2024AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agentscited by 450
  4. 2023Android in the Wild: A Large-Scale Dataset for Android Device Controlcited by 314
  5. 2023Language to Rewards for Robotic Skill Synthesiscited by 307
  6. 2023Large Language Models as Tool Makerscited by 293
  7. 2018Reinforcement Learning on Web Interfaces Using Workflow-Guided Explorationcited by 282
  8. 2023AdaPlanner: Adaptive Planning from Feedback with Language Modelscited by 193
  9. 2023Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Controlcited by 180
  10. 2020DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learningcited by 159
  11. 2024Autonomous Evaluation and Refinement of Digital Agentscited by 136
  12. 2017Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learningcited by 97
8 more
  1. 2023CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalizationcited by 88
  2. 2022Language Models Can Teach Themselves to Program Bettercited by 75
  3. 2024TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Taskscited by 70
  4. 2022Top-Down Synthesis for Library Learningcited by 57
  5. 2024What Are Tools Anyway? A Survey from the Language Model Perspectivecited by 53
  6. 2023LILO: Learning Interpretable Libraries by Compressing and Documenting Codecited by 46
  7. 2024BAGEL: Bootstrapping Agents by Guiding Exploration with Languagecited by 34
  8. 2023Learning Reusable Manipulation Strategiescited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 11; 2025: 72; 2026: 259.

342 papers.

Sort:

By area:

  1. 2025UI-TARS: Pioneering Automated GUI Interaction with Native Agentscited by 584
  2. 2025Why Do Multi-Agent LLM Systems Fail?cited by 559
  3. 2025Agentic Context Engineering: Evolving Contexts for Self-Improving Language Modelscited by 349
  4. 2024Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agentscited by 341
  5. 2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memorycited by 253
  6. 2026SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learningcited by 252
  7. 2024WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learningcited by 243
  8. 2025Plan-and-Act: Improving Planning of Agents for Long-Horizon Taskscited by 190
  9. 2025SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skillscited by 174
  10. 2026Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skillscited by 161
  11. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 155
  12. 2025ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoningcited by 144
38 more
  1. 2026SimpleMem: Efficient Lifelong Memory for LLM Agentscited by 140
  2. 2025Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memorycited by 129
  3. 2026MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agentscited by 129
  4. 2024ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agentscited by 126
  5. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  6. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  7. 2025Memento: Fine-tuning LLM Agents without Fine-tuning LLMscited by 119
  8. 2024Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigationcited by 116
  9. 2025Inducing Programmatic Skills for Agentic Taskscited by 103
  10. 2025In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agentscited by 102
  11. 2024AutoGLM: Autonomous Foundation Agents for GUIscited by 96
  12. 2025How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behaviorcited by 95
  13. 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solvingcited by 90
  14. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 89
  15. 2025MemEvolve: Meta-Evolution of Agent Memory Systemscited by 81
  16. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 78
  17. 2024Beyond Browsing: API-Based Web Agentscited by 77
  18. 2026XSkill: Continual Learning from Experience and Skills in Multimodal Agentscited by 71
  19. 2026SkillX: Automatically Constructing Skill Knowledge Bases for Agentscited by 69
  20. 2025AutoPresent: Designing Structured Visuals from Scratchcited by 63
  21. 2024NNetNav: Unsupervised Learning of Browser Agents Through Environment Interaction in the Wildcited by 55
  22. 2026SkillNet: Create, Evaluate, and Connect AI Skillscited by 48
  23. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  24. 2026AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applicationscited by 46
  25. 2026SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Taskscited by 45
  26. 2026SkillOS: Learning Skill Curation for Self-Evolving Agentscited by 45
  27. 2026Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agentscited by 44
  28. 2025Continuum: Efficient and Robust Multi-Turn LLM Agent Scheduling with KV Cache Time-to-Livecited by 43
  29. 2026Meta Context Engineering via Agentic Skill Evolutioncited by 42
  30. 2025ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoningcited by 41
  31. 2025Web-Shepherd: Advancing PRMs for Reinforcing Web Agentscited by 41
  32. 2024ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Datacited by 39
  33. 2025OS Agents: A Survey on MLLM-based Agents for General Computing Devices Usecited by 35
  34. 2026MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wildcited by 35
  35. 2025Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interactioncited by 34
  36. 2026Dynamic Dual-Granularity Skill Bank for Agentic RLcited by 33
  37. 2026Dive into Claude Code: The Design Space of Today's and Future AI Agent Systemscited by 33
  38. 2025Go-Browse: Training Web Agents with Structured Explorationcited by 32

50 most cited of 342 All 342 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model
  2. 2026AMBER: Training Long-Horizon Web Agents through Append-Only Memory
  3. 2026M2: Dual-Memory Augmentation for Long-Horizon Web Agents via Trajectory Summarization and Insight Retrieval
  4. 2026WebChallenger: A Reliable and Efficient Generalist Web Agent
  5. 2025ReUseIt: Synthesizing Reusable AI Agent Workflows for Web Automation
  6. 2024Unveiling Disparities in Web Task Handling Between Human and Web Agent
  7. 2024AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents
  8. 2024Large Language Models Can Self-Improve At Web Agent Tasks