mlsanityData to 14 Oct 2026

AgentTuning: Enabling Generalized Agent Abilities for LLMs

arXiv 2310.12823 ↗First posted 19 Oct 2023cs.CL cs.AI cs.LGcited by 338

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

Abstract (arXiv)

Open large language models (LLMs) with great performance in various tasks have significantly advanced the development of LLMs. However, they are far inferior to commercial models such as ChatGPT and GPT-4 when acting as agents to tackle complex tasks in the real world. These agent tasks employ LLMs as the central controller responsible for planning, memorization, and tool utilization, necessitating both fine-grained prompting methods and robust LLMs to achieve satisfactory performance. Though many prompting methods have been proposed to complete particular agent tasks, there is lack of research focusing on improving the agent capabilities of LLMs themselves without compromising their general abilities. In this work, we present AgentTuning, a simple and general method to enhance the agent abilities of LLMs while maintaining their general LLM capabilities. We construct AgentInstruct, a lightweight instruction-tuning dataset containing high-quality interaction trajectories. We employ a hybrid instruction-tuning strategy by combining AgentInstruct with open-source instructions from general domains. AgentTuning is used to instruction-tune the Llama 2 series, resulting in AgentLM. Our evaluations show that AgentTuning enables LLMs' agent capabilities without compromising general abilities. The AgentLM-70B is comparable to GPT-3.5-turbo on unseen agent tasks, demonstrating generalized agent capabilities. We open source the AgentInstruct and AgentLM-7B, 13B, and 70B models at https://github.com/THUDM/AgentTuning, serving open and powerful alternatives to commercial LLMs for agent tasks.

Key facts. Cited by 338 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 32 of its 53 references that are in the map. First posted on arXiv 19 Oct 2023.

Builds on

32 of 53 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023AgentBench: Evaluating LLMs as Agents7 Aug

Other references · 31

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  6. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  7. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  8. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  9. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  10. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  11. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  12. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
19 more
  1. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  2. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  3. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  4. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  5. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 2,006
  6. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  7. 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,868
  8. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
  9. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,251
  10. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,242
  11. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
  12. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 843
  13. 2023Large Language Modelscited by 780
  14. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
  15. 2023How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resourcescited by 408
  16. 2023Language Models can Solve Computer Taskscited by 372
  17. 2022ScienceWorld: Is your Agent Smarter than a 5th Grader?cited by 327
  18. 2023OpenChat: Advancing Open-source Language Models with Mixed-Quality Datacited by 252
  19. 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 184

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 9; 2024: 101; 2025: 110; 2026: 118.

338 papers.

Sort:

By area:

  1. 2023CogAgent: A Visual Language Model for GUI Agentscited by 704
  2. 2024Understanding the planning of LLM agents: A surveycited by 421
  3. 2024OS-ATLAS: A Foundation Action Model for Generalist GUI Agentscited by 378
  4. 2024WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?cited by 363
  5. 2025ToolRL: Reward is All Tool Learning Needscited by 362
  6. 2024ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Searchcited by 344
  7. 2024Training Software Engineering Agents and Verifiers with SWE-Gymcited by 336
  8. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 284
  9. 2024WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learningcited by 256
  10. 2025MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agentscited by 238
  11. 2024APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasetscited by 198
  12. 2024Trial and Error: Exploration-Based Trajectory Optimization for LLM Agentscited by 197
38 more
  1. 2025WebDancer: Towards Autonomous Information Seeking Agencycited by 188
  2. 2025WebWalker: Benchmarking LLMs in Web Traversalcited by 175
  3. 2025The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoningcited by 166
  4. 2024Recursive Introspection: Teaching Language Model Agents How to Self-Improvecited by 165
  5. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Reviewcited by 149
  6. 2024InfiAgent-DABench: Evaluating Agents on Data Analysis Taskscited by 140
  7. 2024Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agentscited by 137
  8. 2024Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospectscited by 132
  9. 2025OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automationcited by 131
  10. 2026SoK: Agentic Skills -- Beyond Tool Use in LLM Agentscited by 130
  11. 2024DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoningcited by 125
  12. 2024AgentGym: Evolving Large Language Model-based Agents across Diverse Environmentscited by 120
  13. 2024BadAgent: Inserting and Activating Backdoor Attacks in LLM Agentscited by 115
  14. 2024A Survey on Large Language Model-Based Game Agentscited by 112
  15. 2024xLAM: A Family of Large Action Models to Empower AI Agent Systemscited by 111
  16. 2024On-Device Language Models: A Comprehensive Reviewcited by 104
  17. 2024VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agentscited by 103
  18. 2024Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Modelscited by 100
  19. 2024AutoGLM: Autonomous Foundation Agents for GUIscited by 100
  20. 2025Reinforcement Learning for Self-Improving Agent with Skill Librarycited by 100
  21. 2024Revisiting Catastrophic Forgetting in Large Language Model Tuningcited by 99
  22. 2025Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environmentscited by 95
  23. 2023T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Stepcited by 93
  24. 2024Small LLMs Are Weak Tool Learners: A Multi-LLM Agentcited by 93
  25. 2024Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinementcited by 88
  26. 2025Process Reward Models for LLM Agents: Practical Framework and Directionscited by 85
  27. 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generationcited by 83
  28. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 83
  29. 2025Agent-R: Training Language Model Agents to Reflect via Iterative Self-Trainingcited by 82
  30. 2024AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planningcited by 81
  31. 2024AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agentscited by 74
  32. 2024ToolGen: Unified Tool Retrieval and Calling via Generationcited by 74
  33. 2023LLMLight: Large Language Models as Traffic Signal Control Agentscited by 73
  34. 2025SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attributioncited by 73
  35. 2023Agent Lumos: Unified and Modular Training for Open-Source Language Agentscited by 72
  36. 2024AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoningcited by 72
  37. 2025AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learningcited by 72
  38. 2025DeepAgent: A General Reasoning Agent with Scalable Toolsetscited by 71

50 most cited of 338 All 338 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Enhancing LLM Instruction Following: An Evaluation-Driven Multi-Agentic Workflow for Prompt Instructions Optimization
  2. 2026Computer Environments Elicit General Agentic Intelligence in LLMs
  3. 2025From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users
  4. 2026SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories
  5. 2025AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios
  6. 2025AutoPDL: Automatic Prompt Optimization for LLM Agents
  7. 2024Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning
  8. 2024Learning to Use Tools via Cooperative and Interactive Agents