mlsanityData to 7 Oct 2026

Large Language Models as Tool Makers

arXiv 2305.17126 ↗First posted 26 May 2023cs.LG cs.AI cs.CLcited by 293

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

Abstract (arXiv)

Recent research has highlighted the potential of large language models (LLMs) to improve their problem-solving capabilities with the aid of suitable external tools. In our work, we further advance this concept by introducing a closed-loop framework, referred to as LLMs A s Tool Makers (LATM), where LLMs create their own reusable tools for problem-solving. Our approach consists of two phases: 1) tool making: an LLM acts as the tool maker that crafts tools for a set of tasks. 2) tool using: another LLM acts as the tool user, which applies the tool built by the tool maker for problem-solving. On the problem-solving server side, tool-making enables continual tool generation and caching as new requests emerge. This framework enables subsequent requests to access cached tools via their corresponding APIs, enhancing the efficiency of task resolution. Recognizing that tool-making requires more sophisticated capabilities, we assign this task to a powerful, albeit resource-intensive, model. Conversely, the simpler tool-using phase is delegated to a lightweight model. This strategic division of labor allows the once-off cost of tool-making to be spread over multiple instances of tool-using, significantly reducing average costs while maintaining strong performance. Furthermore, our method offers a functional cache through the caching and reuse of tools, which stores the functionality of a class of requests instead of the natural language responses from LLMs, thus extending the applicability of the conventional cache mechanism. We evaluate our approach across various complex reasoning tasks, including Big-Bench tasks. With GPT-4 as the tool maker and GPT-3.5 as the tool user, LATM demonstrates performance equivalent to using GPT-4 for both roles, but with a significantly reduced inference cost.

Key facts. Cited by 293 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 37 of its 43 references that are in the map. First posted on arXiv 26 May 2023.

Builds on

37 of 43 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Tool Learning with Foundation Models17 Apr
  2. 2023ART: Automatic multi-step reasoning and tool-use for large language models16 Mar
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Tools9 Feb
  4. 2022TALM: Tool Augmented Language Models24 May

Other references · 33

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  7. 2021Program Synthesis with Large Language Modelscited by 3,509
  8. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  9. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  10. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  11. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  12. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
21 more
  1. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  2. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  3. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,615
  4. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  5. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
  6. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  7. 2023Accelerating Large Language Model Decoding with Speculative Samplingcited by 975
  8. 2023Teaching Large Language Models to Self-Debugcited by 963
  9. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 871
  10. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 791
  11. 2019MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalismscited by 653
  12. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 642
  13. 2022Language Models are Multilingual Chain-of-Thought Reasonerscited by 518
  14. 2023MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Actioncited by 511
  15. 2023Language Models can Solve Computer Taskscited by 371
  16. 2023Chameleon: Plug-and-Play Compositional Reasoning with Large Language Modelscited by 352
  17. 2021AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Promptscited by 265
  18. 2023TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIscited by 184
  19. 2023Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakescited by 101
  20. 2021Neural Algorithmic Reasoningcited by 92
  21. 2022Mind's Eye: Grounded Language Model Reasoning through Simulationcited by 83

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 56; 2024: 93; 2025: 64; 2026: 80.

293 papers.

Sort:

By area:

  1. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  2. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  3. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  4. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  5. 2023ChatDev: Communicative Agents for Software Developmentcited by 893
  6. 2023Large Language Models as Optimizerscited by 830
  7. 2023Prompt Injection attack against LLM-integrated Applicationscited by 568
  8. 2023How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resourcescited by 405
  9. 2024Scaling Synthetic Data Creation with 1,000,000,000 Personascited by 397
  10. 2024Agent Workflow Memorycited by 342
  11. 2023Visual Adversarial Examples Jailbreak Aligned Large Language Modelscited by 307
  12. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 276
38 more
  1. 2023Multimodal Foundation Models: From Specialists to General-Purpose Assistantscited by 247
  2. 2023Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaborationcited by 246
  3. 2024Capabilities of Gemini Models in Medicinecited by 231
  4. 2024Data Interpreter: An LLM Agent For Data Sciencecited by 222
  5. 2024Tool Learning with Large Language Models: A Surveycited by 221
  6. 2023MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Usecited by 209
  7. 2024OS-Copilot: Towards Generalist Computer Agents with Self-Improvementcited by 203
  8. 2023Evaluating Large Language Models: A Comprehensive Surveycited by 200
  9. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  10. 2025SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skillscited by 174
  11. 2023DistillSpec: Improving Speculative Decoding via Knowledge Distillationcited by 160
  12. 2025APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplaycited by 158
  13. 2025Prompt Injection Attack to Tool Selection in LLM Agentscited by 145
  14. 2023Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoningcited by 140
  15. 2023OpenAgents: An Open Platform for Language Agents in the Wildcited by 136
  16. 2024StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Modelscited by 129
  17. 2023Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generationcited by 128
  18. 2025Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Taskscited by 128
  19. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  20. 2023CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsetscited by 122
  21. 2024AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Callscited by 121
  22. 2024LLM Multi-Agent Systems: Challenges and Open Problemscited by 119
  23. 2024Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversationscited by 118
  24. 2024Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffoldingcited by 115
  25. 2024FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Makingcited by 112
  26. 2023LEGO-Prover: Neural Theorem Proving with Growing Librariescited by 108
  27. 2023Large Language Models as Analogical Reasonerscited by 107
  28. 2026Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forwardcited by 105
  29. 2023Evil Geniuses: Delving into the Safety of LLM-based Agentscited by 103
  30. 2025Inducing Programmatic Skills for Agentic Taskscited by 103
  31. 2025Multi-Agent Collaboration via Evolving Orchestrationcited by 102
  32. 2024A Review of Large Language Models and Autonomous Agents in Chemistrycited by 96
  33. 2023Frontier AI Regulation: Managing Emerging Risks to Public Safetycited by 95
  34. 2024From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflectioncited by 93
  35. 2025Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?cited by 91
  36. 2025Reinforcement Learning for Self-Improving Agent with Skill Librarycited by 91
  37. 2023When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunitiescited by 89
  38. 2024The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Modelscited by 89

50 most cited of 293 All 293 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025TUMS: Enhancing Tool-use Abilities of LLMs with Multi-structure Handlers
  2. 2025ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filtering
  3. 2025OR-Toolformer: Modeling and Solving Operations Research Problems with Tool Augmented Large Language Models
  4. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs
  5. 2024Towards Practical Tool Usage for Continually Learning LLMs
  6. 2026Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool Primitives
  7. 2024Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents
  8. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs