mlsanityData to 14 Oct 2026

AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning

arXiv 2401.05268 ↗First posted 10 Jan 2024cs.CL cs.AI cs.HCcited by 81

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

Abstract (arXiv)

Language agents have achieved considerable performance on various complex question-answering tasks by planning with external tools. Despite the incessant exploration in this field, existing language agent systems still struggle with costly, non-reproducible data reliance and face the challenge of compelling a single model for multiple functions. To this end, we introduce AutoAct, an automatic agent learning framework for QA that does not rely on large-scale annotated data and synthetic planning trajectories from closed-source models (e.g., GPT-4). Given limited data with a tool library, AutoAct first automatically synthesizes planning trajectories without any assistance from humans or strong closed-source models. Then, AutoAct leverages a division-of-labor strategy to automatically differentiate based on the target task information and synthesized trajectories, producing a sub-agent group to complete the task. We conduct comprehensive experiments with different LLMs, which demonstrates that AutoAct yields better or parallel performance compared to various strong baselines. Further analysis demonstrates the effectiveness of the division-of-labor strategy, with the trajectory quality generated by AutoAct generally outperforming that of others. Code will be available at https://github.com/zjunlp/AutoAct.

Key facts. Cited by 81 papers in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 39 of its 66 references that are in the map. First posted on arXiv 10 Jan 2024.

Builds on

39 of 66 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023WebArena: A Realistic Web Environment for Building Autonomous Agents25 Jul
  2. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents4 Jul

Other references · 37

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  6. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  7. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  8. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  9. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  10. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  11. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,919
  12. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
25 more
  1. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  2. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  3. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
  4. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  5. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
  6. 2022Large Language Models Can Self-Improvecited by 664
  7. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 598
  8. 2023Reinforced Self-Training (ReST) for Language Modelingcited by 500
  9. 2018VirtualHome: Simulating Household Activities via Programscited by 415
  10. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMscited by 338
  11. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agentscited by 333
  12. 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoningcited by 316
  13. 2023ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMscited by 309
  14. 2023FireAct: Toward Language Agent Fine-tuningcited by 256
  15. 2022Reasoning with Language Model Prompting: A Surveycited by 252
  16. 2023Specializing Smaller Language Models towards Multi-Step Reasoningcited by 251
  17. 2023AutoAgents: A Framework for Automatic Agent Generationcited by 216
  18. 2021Generated Knowledge Prompting for Commonsense Reasoningcited by 214
  19. 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 184
  20. 2023JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Modelscited by 171
  21. 2023OpenAgents: An Open Platform for Language Agents in the Wildcited by 137
  22. 2023Language Models Meet World Models: Embodied Experiences Enhance Language Modelscited by 124
  23. 2023BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agentscited by 84
  24. 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agentscited by 72
  25. 2023Making Language Models Better Tool Learners with Execution Feedbackcited by 70

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 18; 2025: 41; 2026: 22.

81 papers.

Sort:

By area:

  1. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 431
  2. 2024Quiet-STaR: Language Models Can Teach Themselves to Think Before Speakingcited by 301
  3. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Modelscited by 293
  4. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 284
  5. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 205
  6. 2025WebDancer: Towards Autonomous Information Seeking Agencycited by 188
  7. 2025WebWalker: Benchmarking LLMs in Web Traversalcited by 175
  8. 2024Continual Learning for Large Language Models: A Surveycited by 147
  9. 2025Multi-Agent Design: Optimizing Agents with Better Prompts and Topologiescited by 113
  10. 2024Symbolic Learning Enables Self-Evolving Agentscited by 106
  11. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 77
  12. 2024ToolGen: Unified Tool Retrieval and Calling via Generationcited by 74
38 more
  1. 2024Direct Multi-Turn Preference Optimization for Language Agentscited by 64
  2. 2024Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Surveycited by 53
  3. 2025TaskCraft: Automated Generation of Agentic Taskscited by 51
  4. 2024Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agentscited by 50
  5. 2025Distilling LLM Agent into Small Models with Retrieval and Code Toolscited by 47
  6. 2025A Survey on the Optimization of Large Language Model-based Agentscited by 46
  7. 2024A Multi-Agent Conversational Recommender Systemcited by 43
  8. 2024Benchmarking Agentic Workflow Generationcited by 37
  9. 2025A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrievalcited by 33
  10. 2025From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Userscited by 32
  11. 2025ATLaS: Agent Tuning via Learning Critical Stepscited by 31
  12. 2025Internet of Agents: Fundamentals, Applications, and Challengescited by 31
  13. 2025Embodied AI: From LLMs to World Modelscited by 24
  14. 2025AutoMind: Adaptive Knowledgeable Agent for Automated Data Sciencecited by 20
  15. 2026Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judgecited by 18
  16. 2025Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planningcited by 17
  17. 2026SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scalecited by 16
  18. 2025AgentSwift: Efficient LLM Agent Design via Value-guided Hierarchical Searchcited by 15
  19. 2025Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMscited by 14
  20. 2024Smurfs: Multi-Agent System using Context-Efficient DFSDT for Tool Planningcited by 13
  21. 2024Efficient Multi-Agent Collaboration with Tool Use for Online Planning in Complex Table Question Answeringcited by 13
  22. 2025Prune4Web: DOM Tree Pruning Programming for Web Agentcited by 12
  23. 2024RescueADI: Adaptive Disaster Interpretation in Remote Sensing Images with Autonomous Agentscited by 11
  24. 2025Advancing Language Multi-Agent Learning with Credit Re-Assignment for Interactive Environment Generalizationcited by 11
  25. 2025Exploring Advanced LLM Multi-Agent Systems Based on Blackboard Architecturecited by 11
  26. 2025Scaling Generalist Data-Analytic Agentscited by 11
  27. 2026LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agentscited by 10
  28. 2026The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMscited by 10
  29. 2024Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoningcited by 9
  30. 2025HiMA-Ecom: Enabling Joint Training of Hierarchical Multi-Agent E-commerce Assistantscited by 9
  31. 2026Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learningcited by 9
  32. 2024ReDel: A Toolkit for LLM-Powered Recursive Multi-Agent Systemscited by 8
  33. 2025The Power of Personality: A Human Simulation Perspective to Investigate Large Language Model Agentscited by 8
  34. 2025iTool: Reinforced Fine-Tuning with Dynamic Deficiency Calibration for Advanced Tool Usecited by 7
  35. 2025Why Do Open-Source LLMs Struggle with Data Analysis? A Systematic Empirical Studycited by 7
  36. 2025Graph2Eval: Automatic Multimodal Task Generation for Agents via Knowledge Graphscited by 7
  37. 2026DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent Behaviorscited by 7
  38. 2026Retrieval-Augmented LLM Agents: Learning to Learn from Experiencecited by 7

50 most cited of 81 All 81 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models
  2. 2026AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question Answering
  3. 2025ALAS: Autonomous Learning Agent for Self-Updating Language Models
  4. 2026GraphWalker: Agentic Knowledge Graph Question Answering via Synthetic Trajectory Curriculum
  5. 2026ACC: Compiling Agent Trajectories for Long-Context Training
  6. 2024Ask-before-Plan: Proactive Language Agents for Real-World Planning
  7. 2024Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents
  8. 2024ReAct Meets ActRe: When Language Agents Enjoy Training Data Autonomy