mlsanityData to 7 Oct 2026

ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases

arXiv 2306.05301 ↗First posted 8 Jun 2023cs.CLcited by 383

On the map: LLM agents and tool use → Tool learning and function calling

Abstract (arXiv)

Enabling large language models to utilize real-world tools effectively is crucial for achieving embodied intelligence. Existing approaches to tool learning have either primarily relied on extremely large language models, such as GPT-4, to attain generalized tool-use abilities in a zero-shot manner, or utilized supervised learning to train limited scopes of tools on compact models. However, it remains uncertain whether smaller language models can achieve generalized tool-use abilities without tool-specific training. To address this question, this paper introduces ToolAlpaca, a novel framework designed to automatically generate a diverse tool-use corpus and learn generalized tool-use abilities on compact language models with minimal human intervention. Specifically, ToolAlpaca first automatically creates a highly diversified tool-use corpus by building a multi-agent simulation environment. The corpus contains 3938 tool-use instances from more than 400 real-world tool APIs spanning 50 distinct categories. Subsequently, the constructed corpus is employed to fine-tune compact language models, resulting in two models, namely ToolAlpaca-7B and ToolAlpaca-13B, respectively. Finally, we evaluate the ability of these models to utilize previously unseen tools without specific training. Experimental results demonstrate that ToolAlpaca achieves effective generalized tool-use capabilities comparable to those of extremely large language models like GPT-3.5, demonstrating that learning generalized tool-use ability is feasible for compact language models.

Key facts. Cited by 383 papers in the map (data through 7 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 21 of its 31 references that are in the map. First posted on arXiv 8 Jun 2023.

Builds on

21 of 31 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction30 May
  2. 2023Gorilla: Large Language Model Connected with Massive APIs24 May
  3. 2023Tool Learning with Foundation Models17 Apr
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Tools9 Feb
  5. 2022TALM: Tool Augmented Language Models24 May

Other references · 16

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  5. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
  6. 2023LIMA: Less Is More for Alignmentcited by 1,080
  7. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  8. 2022PAL: Program-aided Language Modelscited by 635
  9. 2022Unnatural Instructions: Tuning Language Models with (Almost) No Human Laborcited by 395
  10. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 316
  11. 2021Internet-Augmented Dialogue Generationcited by 217
  12. 2021Want To Reduce Labeling Cost? GPT-3 Can Helpcited by 196
4 more
  1. 2021Generating Datasets with Pretrained Language Modelscited by 192
  2. 2023On the Tool Manipulation Capability of Open-source Large Language Modelscited by 122
  3. 2022QAmeleon: Multilingual QA with Only 5 Examplescited by 25
  4. 2023Few-Shot Data Synthesis for Open Domain Multi-Hop Question Answeringcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 27; 2024: 111; 2025: 115; 2026: 130.

383 papers.

Sort:

By area:

  1. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  2. 2023Identifying the Risks of LM Agents with an LM-Emulated Sandboxcited by 514
  3. 2023Cognitive Architectures for Language Agentscited by 422
  4. 2023MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedbackcited by 293
  5. 2026Reinforcement Learning via Self-Distillationcited by 285
  6. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 276
  7. 2024Tool Learning with Large Language Models: A Surveycited by 221
  8. 2026Self-Distillation Enables Continual Learningcited by 212
  9. 2023MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Usecited by 209
  10. 2024ToolACE: Winning the Points of LLM Function Callingcited by 204
  11. 2023Evaluating Large Language Models: A Comprehensive Surveycited by 200
  12. 2025Survey on Evaluation of LLM-based Agentscited by 190
38 more
  1. 2024APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasetscited by 188
  2. 2025RL's Razor: Why Online Reinforcement Learning Forgets Lesscited by 162
  3. 2024AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?cited by 155
  4. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 155
  5. 2024EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instructioncited by 153
  6. 2023TaskBench: Benchmarking Large Language Models for Task Automationcited by 138
  7. 2023RestGPT: Connecting Large Language Models with Real-World RESTful APIscited by 129
  8. 2024StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Modelscited by 129
  9. 2024AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agentscited by 129
  10. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  11. 2023CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsetscited by 122
  12. 2024AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Callscited by 121
  13. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 110
  14. 2024xLAM: A Family of Large Action Models to Empower AI Agent Systemscited by 108
  15. 2025Agentic Large Language Models, a surveycited by 105
  16. 2026AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolutioncited by 105
  17. 2024Best Practices and Lessons Learned on Synthetic Datacited by 104
  18. 2024AIOS: LLM Agent Operating Systemcited by 94
  19. 2024Small LLMs Are Weak Tool Learners: A Multi-LLM Agentcited by 92
  20. 2024The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agentscited by 89
  21. 2026Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?cited by 87
  22. 2024Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarioscited by 85
  23. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 78
  24. 2024If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agentscited by 77
  25. 2024ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stagescited by 77
  26. 2024MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learningcited by 66
  27. 2024Agent Planning with World Knowledge Modelcited by 66
  28. 2024Inadequacies of Large Language Model Benchmarks in the Era of Generative Artificial Intelligencecited by 65
  29. 2026Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routingcited by 65
  30. 2023Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculumcited by 64
  31. 2024Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmarkcited by 62
  32. 2025TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environmentscited by 61
  33. 2024Towards Lifelong Learning of Large Language Models: A Surveycited by 60
  34. 2024LLM With Tools: A Surveycited by 60
  35. 2023ControlLLM: Augment Language Models with Tools by Searching on Graphscited by 59
  36. 2024ToolNet: Connecting Large Language Models with Massive Tools via Tool Graphcited by 59
  37. 2024Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agentscited by 56
  38. 2025G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systemscited by 56

50 most cited of 383 All 383 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026RaTA-Tool: Retrieval-based Tool Selection with Multimodal Large Language Models
  2. 2024GTA: A Benchmark for General Tool Agents
  3. 2025ToolMind Technical Report: A Large-Scale, Reasoning-Enhanced Tool-Use Dataset
  4. 2025Tool-R1: Sample-Efficient Reinforcement Learning for Agentic Tool Use
  5. 2026Evolve Vision-Language-Action Model into an Agent with On-the-fly Tool-use
  6. 2026ToolOmni: Enabling Open-World Tool Use via Agentic learning with Proactive Retrieval and Grounded Execution
  7. 2025Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning
  8. 2024From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons