mlsanityData to 14 Oct 2026

Tool Learning with Foundation Models

arXiv 2304.08354 ↗First posted 17 Apr 2023cs.CL cs.AI cs.LGcited by 302

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

Abstract (arXiv)

Humans possess an extraordinary ability to create and utilize tools, allowing them to overcome physical limitations and explore new frontiers. With the advent of foundation models, AI systems have the potential to be equally adept in tool use as humans. This paradigm, i.e., tool learning with foundation models, combines the strengths of specialized tools and foundation models to achieve enhanced accuracy, efficiency, and automation in problem-solving. Despite its immense potential, there is still a lack of a comprehensive understanding of key challenges, opportunities, and future endeavors in this field. To this end, we present a systematic investigation of tool learning in this paper. We first introduce the background of tool learning, including its cognitive origins, the paradigm shift of foundation models, and the complementary roles of tools and models. Then we recapitulate existing tool learning research into tool-augmented and tool-oriented learning. We formulate a general tool learning framework: starting from understanding the user instruction, models should learn to decompose a complex task into several subtasks, dynamically adjust their plan through reasoning, and effectively conquer each sub-task by selecting appropriate tools. We also discuss how to train models for improved tool-use capabilities and facilitate the generalization in tool learning. Considering the lack of a systematic tool learning evaluation in prior works, we experiment with 18 representative tools and show the potential of current foundation models in skillfully utilizing tools. Finally, we discuss several open problems that require further investigation for tool learning. In general, we hope this paper could inspire future research in integrating tools with foundation models.

Key facts. Cited by 302 papers in the map (data through 14 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 137 of its 243 references that are in the map. First posted on arXiv 17 Apr 2023.

Builds on

137 of 243 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Toolformer: Language Models Can Teach Themselves to Use Tools9 Feb
  2. 2022TALM: Tool Augmented Language Models24 May

Other references · 135

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2022Training language models to follow instructions with human feedbackcited by 15,971
  6. 2017Proximal Policy Optimization Algorithmscited by 15,215
  7. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  8. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  9. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  10. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  11. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  12. 2021Evaluating Large Language Models Trained on Codecited by 8,320
38 more
  1. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  3. 2013Intriguing properties of neural networkscited by 5,155
  4. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  5. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  6. 2017Deep reinforcement learning from human preferencescited by 3,912
  7. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  8. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  9. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  10. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  11. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  12. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  13. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  14. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  15. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  16. 2020Learning to summarize from human feedbackcited by 2,588
  17. 2022Emergent Abilities of Large Language Modelscited by 2,512
  18. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  19. 2020Extracting Training Data from Large Language Modelscited by 2,189
  20. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  21. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  22. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  23. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  24. 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,729
  25. 2016Concrete Problems in AI Safetycited by 1,642
  26. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
  27. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
  28. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,312
  29. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  30. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,251
  31. 2022LaMDA: Language Models for Dialog Applicationscited by 1,220
  32. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  33. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,210
  34. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
  35. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
  36. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,103
  37. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,081
  38. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076

50 most cited of 135 All 135 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 74; 2024: 80; 2025: 84; 2026: 64.

302 papers.

Sort:

By area:

  1. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  2. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  3. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  4. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,242
  5. 2023A Survey on Evaluation of Large Language Modelscited by 1,242
  6. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 634
  7. 2023LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Modelcited by 602
  8. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 598
  9. 2024Executable Code Actions Elicit Better LLM Agentscited by 564
  10. 2024BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructionscited by 546
  11. 2024Understanding the planning of LLM agents: A surveycited by 421
  12. 2023UltraFeedback: Boosting Language Models with Scaled AI Feedbackcited by 406
38 more
  1. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Casescited by 393
  2. 2025ToolRL: Reward is All Tool Learning Needscited by 362
  3. 2023Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflictscited by 341
  4. 2024AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agentscited by 339
  5. 2023Large Language Models as Tool Makerscited by 303
  6. 2023MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedbackcited by 297
  7. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Securitycited by 260
  8. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectivescited by 257
  9. 2023Large Language Model Alignment: A Surveycited by 243
  10. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddingscited by 240
  11. 2024Tool Learning with Large Language Models: A Surveycited by 223
  12. 2023MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Usecited by 217
  13. 2024OS-Copilot: Towards Generalist Computer Agents with Self-Improvementcited by 205
  14. 2023Evaluating Large Language Models: A Comprehensive Surveycited by 202
  15. 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 184
  16. 2023Can LLM-Generated Misinformation Be Detected?cited by 177
  17. 2023RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Modelscited by 175
  18. 2025APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplaycited by 167
  19. 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 163
  20. 2024Large Legal Fictions: Profiling Legal Hallucinations in Large Language Modelscited by 150
  21. 2023TaskBench: Benchmarking Large Language Models for Task Automationcited by 144
  22. 2023OpenAgents: An Open Platform for Language Agents in the Wildcited by 137
  23. 2024Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agentscited by 137
  24. 2023RestGPT: Connecting Large Language Models with Real-World RESTful APIscited by 135
  25. 2023Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Modelscited by 133
  26. 2023Large Language Models for Robotics: A Surveycited by 133
  27. 2024Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospectscited by 132
  28. 2026SoK: Agentic Skills -- Beyond Tool Use in LLM Agentscited by 130
  29. 2023CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsetscited by 129
  30. 2024EfficientQAT: Efficient Quantization-Aware Training for Large Language Modelscited by 127
  31. 2024AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Callscited by 124
  32. 2023On the Tool Manipulation Capability of Open-source Large Language Modelscited by 122
  33. 2023Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Healthcited by 118
  34. 2023ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Searchcited by 105
  35. 2025Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understandingcited by 98
  36. 2025A Survey on Trustworthy LLM Agents: Threats and Countermeasurescited by 96
  37. 2023CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Modelscited by 93
  38. 2024Small LLMs Are Weak Tool Learners: A Multi-LLM Agentcited by 93

50 most cited of 302 All 302 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025ToolComp: A Multi-Tool Reasoning & Process Supervision Benchmark
  2. 2026Teaching LLMs to Learn Tool Trialing and Execution through Environment Interaction
  3. 2026Joint Optimization of Tool Creation and Use for Large Language Model Agents
  4. 2026Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoning
  5. 2026Beyond APIs: Probing the Limits of MLLMs in Physical Tool Use
  6. 2026ToolOmni: Enabling Open-World Tool Use via Agentic learning with Proactive Retrieval and Grounded Execution
  7. 2025Advanced Tool Learning and Selection System (ATLASS): A Closed-Loop Framework Using LLM
  8. 2024FoundationGrasp: Generalizable Task-Oriented Grasping with Foundation Models