mlsanityData to 14 Oct 2026

Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models

arXiv 2403.12881 ↗First posted 19 Mar 2024cs.CLcited by 100

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Open-sourced Large Language Models (LLMs) have achieved great success in various NLP tasks, however, they are still far inferior to API-based models when acting as agents. How to integrate agent ability into general LLMs becomes a crucial and urgent problem. This paper first delivers three key observations: (1) the current agent training corpus is entangled with both formats following and agent reasoning, which significantly shifts from the distribution of its pre-training data; (2) LLMs exhibit different learning speeds on the capabilities required by agent tasks; and (3) current approaches have side-effects when improving agent abilities by introducing hallucinations. Based on the above findings, we propose Agent-FLAN to effectively Fine-tune LANguage models for Agents. Through careful decomposition and redesign of the training corpus, Agent-FLAN enables Llama2-7B to outperform prior best works by 3.5% across various agent evaluation datasets. With comprehensively constructed negative samples, Agent-FLAN greatly alleviates the hallucination issues based on our established evaluation benchmark. Besides, it consistently improves the agent capability of LLMs when scaling model sizes while slightly enhancing the general capability of LLMs. The code will be available at https://github.com/InternLM/Agent-FLAN.

Key facts. Cited by 100 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 48 of its 57 references that are in the map. First posted on arXiv 19 Mar 2024.

Builds on

48 of 57 references.

Closest ancestors · 9

Same direction, newest first

  1. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMs19 Oct
  2. 2023FireAct: Toward Language Agent Fine-tuning9 Oct
  3. 2023The Rise and Potential of Large Language Model Based Agents: A Survey14 Sep
  4. 2023Cognitive Architectures for Language Agents5 Sep
  5. 2023A Survey on Large Language Model based Autonomous Agents22 Aug
  6. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors21 Aug
  7. 2023AgentBench: Evaluating LLMs as Agents7 Aug
  8. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug
  9. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents5 Jun

Other references · 39

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  5. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  7. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  8. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  9. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  10. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  11. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  12. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 2,006
27 more
  1. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  2. 2024Mixtral of Expertscited by 1,823
  3. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
  4. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  5. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,251
  6. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,242
  7. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
  8. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,081
  9. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
  10. 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuningcited by 739
  11. 2023Textbooks Are All You Needcited by 569
  12. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 462
  13. 2023GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Ciphercited by 423
  14. 2023Augmented Language Models: a Surveycited by 403
  15. 2022Unnatural Instructions: Tuning Language Models with (Almost) No Human Laborcited by 397
  16. 2023Language Models can Solve Computer Taskscited by 372
  17. 2023Multi-step Jailbreaking Privacy Attacks on ChatGPTcited by 333
  18. 2022ScienceWorld: Is your Agent Smarter than a 5th Grader?cited by 327
  19. 2023ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solvingcited by 282
  20. 2023Specializing Smaller Language Models towards Multi-Step Reasoningcited by 251
  21. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 222
  22. 2021Generated Knowledge Prompting for Commonsense Reasoningcited by 214
  23. 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 184
  24. 2023InstructUIE: Multi-task Instruction Tuning for Unified Information Extractioncited by 170
  25. 2023Full Parameter Fine-tuning for Large Language Models with Limited Resourcescited by 134
  26. 2023Making Language Models Better Tool Learners with Execution Feedbackcited by 70
  27. 2023Editing Personality for Large Language Modelscited by 22

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 21; 2025: 44; 2026: 35.

100 papers.

Sort:

By area:

  1. 2024OS-ATLAS: A Foundation Action Model for Generalist GUI Agentscited by 378
  2. 2025ToolRL: Reward is All Tool Learning Needscited by 362
  3. 2024SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuningcited by 355
  4. 2025MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agentscited by 238
  5. 2024Advancing LLM Reasoning Generalists with Preference Treescited by 192
  6. 2025WebDancer: Towards Autonomous Information Seeking Agencycited by 188
  7. 2025WebWalker: Benchmarking LLMs in Web Traversalcited by 175
  8. 2025APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplaycited by 167
  9. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Reviewcited by 149
  10. 2025OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automationcited by 131
  11. 2024AgentGym: Evolving Large Language Model-based Agents across Diverse Environmentscited by 120
  12. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 116
38 more
  1. 2024xLAM: A Family of Large Action Models to Empower AI Agent Systemscited by 111
  2. 2025MemGen: Weaving Generative Latent Memory for Self-Evolving Agentscited by 109
  3. 2025Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environmentscited by 95
  4. 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generationcited by 83
  5. 2025Agent-R: Training Language Model Agents to Reflect via Iterative Self-Trainingcited by 82
  6. 2024Beyond Browsing: API-Based Web Agentscited by 78
  7. 2024GTA: A Benchmark for General Tool Agentscited by 77
  8. 2024ToolGen: Unified Tool Retrieval and Calling via Generationcited by 74
  9. 2025SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attributioncited by 73
  10. 2025AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learningcited by 72
  11. 2024Agent Planning with World Knowledge Modelcited by 70
  12. 2025VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learningcited by 68
  13. 2024MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Seriescited by 67
  14. 2024MindSearch: Mimicking Human Minds Elicits Deep AI Searchercited by 66
  15. 2026Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learningcited by 66
  16. 2025Towards General Agentic Intelligence via Environment Scalingcited by 54
  17. 2025AgentRefine: Enhancing Agent Generalization through Refinement Tuningcited by 53
  18. 2025Distilling LLM Agent into Small Models with Retrieval and Code Toolscited by 47
  19. 2025A Survey on the Optimization of Large Language Model-based Agentscited by 46
  20. 2025VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agentscited by 45
  21. 2024Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at Scalecited by 43
  22. 2026SkillGen: Verified Inference-Time Agent Skill Synthesiscited by 36
  23. 2026Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Datacited by 34
  24. 2024DynaSaur: Large Language Agents Beyond Predefined Actionscited by 32
  25. 2025Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Gamescited by 31
  26. 2026AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agentscited by 31
  27. 2025Self-Improving LLM Agents at Test-Timecited by 30
  28. 2024Can We Rely on LLM Agents to Draft Long-Horizon Plans? Let's Take TravelPlanner as an Examplecited by 22
  29. 2025Mid-Training of Large Language Models: A Surveycited by 21
  30. 2025SABER: Small Actions, Big Errors -- Safeguarding Mutating Steps in LLM Agentscited by 21
  31. 2025The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvementcited by 20
  32. 2025Test-Time Adaptation for LLM Agents via Environment Interactioncited by 20
  33. 2025Generalizable End-to-End Tool-Use RL with Synthetic CodeGymcited by 17
  34. 2025Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agentscited by 17
  35. 2024Vision Search Assistant: Empower Vision-Language Models as Multimodal Search Enginescited by 16
  36. 2026Toward Efficient Agents: Memory, Tool learning, and Planningcited by 16
  37. 2026Multi-Turn On-Policy Distillation with Prefix Replaycited by 15
  38. 2024ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Modelscited by 14

50 most cited of 100 All 100 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning
  2. 2024Offline Training of Language Model Agents with Functions as Learnable Weights
  3. 2024Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents
  4. 2025Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents
  5. 2025ATLaS: Agent Tuning via Learning Critical Steps
  6. 2026AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments
  7. 2026Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agents
  8. 2026FT-Dojo: Towards Autonomous LLM Fine-Tuning with Language Agents