mlsanityData to 7 Oct 2026

ART: Automatic multi-step reasoning and tool-use for large language models

arXiv 2303.09014 ↗First posted 16 Mar 2023cs.CLcited by 193

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
Abstract (arXiv)

Large language models (LLMs) can perform complex reasoning in few- and zero-shot settings by generating intermediate chain of thought (CoT) reasoning steps. Further, each reasoning step can rely on external tools to support computation beyond the core LLM capabilities (e.g. search/running code). Prior work on CoT prompting and tool use typically requires hand-crafting task-specific demonstrations and carefully scripted interleaving of model generations with tool use. We introduce Automatic Reasoning and Tool-use (ART), a framework that uses frozen LLMs to automatically generate intermediate reasoning steps as a program. Given a new task to solve, ART selects demonstrations of multi-step reasoning and tool use from a task library. At test time, ART seamlessly pauses generation whenever external tools are called, and integrates their output before resuming generation. ART achieves a substantial improvement over few-shot prompting and automatic CoT on unseen tasks in the BigBench and MMLU benchmarks, and matches performance of hand-crafted CoT prompts on a majority of these tasks. ART is also extensible, and makes it easy for humans to improve performance by correcting errors in task-specific programs or incorporating new tools, which we demonstrate by drastically improving performance on select tasks with minimal human intervention.

Key facts. Cited by 193 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 33 of its 40 references that are in the map. First posted on arXiv 16 Mar 2023.

Builds on

33 of 40 references.

References · 33

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  6. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  7. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  8. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  9. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  10. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  11. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  12. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
21 more
  1. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  2. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  3. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  4. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  5. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  6. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  7. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  8. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 915
  9. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 886
  10. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
  11. 2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 696
  12. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 684
  13. 2022PAL: Program-aided Language Modelscited by 635
  14. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 554
  15. 2020UnifiedQA: Crossing Format Boundaries With a Single QA Systemcited by 475
  16. 2021Internet-Augmented Dialogue Generationcited by 217
  17. 2022TALM: Tool Augmented Language Modelscited by 197
  18. 2022Ask Me Anything: A simple strategy for prompting language modelscited by 155
  19. 2022Prompting Is Programming: A Query Language for Large Language Modelscited by 110
  20. 2022Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completioncited by 102
  21. 2022Successive Prompting for Decomposing Complex Questionscited by 94

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 56; 2024: 60; 2025: 43; 2026: 34.

193 papers.

Sort:

By area:

  1. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
  2. 2023The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)cited by 677
  3. 2023A Comprehensive Overview of Large Language Modelscited by 639
  4. 2023Prompt Injection attack against LLM-integrated Applicationscited by 568
  5. 2024Large Language Models: A Surveycited by 506
  6. 2024A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applicationscited by 428
  7. 2023Language Models can Solve Computer Taskscited by 371
  8. 2023Chameleon: Plug-and-Play Compositional Reasoning with Large Language Modelscited by 352
  9. 2023Large Language Models as Tool Makerscited by 293
  10. 2023MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedbackcited by 293
  11. 2023ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solvingcited by 276
  12. 2023ToolQA: A Dataset for LLM Question Answering with External Toolscited by 273
38 more
  1. 2023Multimodal Foundation Models: From Specialists to General-Purpose Assistantscited by 247
  2. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddingscited by 238
  3. 2024Data Interpreter: An LLM Agent For Data Sciencecited by 222
  4. 2024Tool Learning with Large Language Models: A Surveycited by 221
  5. 2024Magentic-One: A Generalist Multi-Agent System for Solving Complex Taskscited by 221
  6. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  7. 2023TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIscited by 184
  8. 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 174
  9. 2024Large Language Model-Based Agents for Software Engineering: A Surveycited by 173
  10. 2023ChatDB: Augmenting LLMs with Databases as Their Symbolic Memorycited by 136
  11. 2024Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoningcited by 136
  12. 2023RestGPT: Connecting Large Language Models with Real-World RESTful APIscited by 129
  13. 2023CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsetscited by 122
  14. 2023Chain of Code: Reasoning with a Language Model-Augmented Code Emulatorcited by 120
  15. 2024AgentScope: A Flexible yet Robust Multi-Agent Platformcited by 120
  16. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  17. 2024FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Makingcited by 112
  18. 2025Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learningcited by 107
  19. 2024OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Modelscited by 105
  20. 2026AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolutioncited by 105
  21. 2023ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Searchcited by 103
  22. 2024LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigationcited by 92
  23. 2024The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Modelscited by 89
  24. 2023AutoML-GPT: Automatic Machine Learning with GPTcited by 80
  25. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 78
  26. 2023MathChat: Converse to Tackle Challenging Math Problems with LLM Agentscited by 67
  27. 2025Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoningcited by 67
  28. 2023Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Modelscited by 66
  29. 2024StateFlow: Enhancing LLM Task-Solving through State-Driven Workflowscited by 65
  30. 2023Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculumcited by 64
  31. 2025AgentRxiv: Towards Collaborative Autonomous Researchcited by 64
  32. 2023Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planningcited by 59
  33. 2023Grammar Prompting for Domain-Specific Language Generation with Large Language Modelscited by 58
  34. 2024Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thoughtcited by 56
  35. 2023TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usagecited by 54
  36. 2023SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Modelscited by 53
  37. 2024What Are Tools Anyway? A Survey from the Language Model Perspectivecited by 53
  38. 2023Self-Verification Improves Few-Shot Clinical Information Extractioncited by 52

50 most cited of 193 All 193 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates
  2. 2026Opening the Black Box: A Survey on the Mechanisms of Multi-Step Reasoning in Large Language Models
  3. 2024Break the Chain: Large Language Models Can be Shortcut Reasoners
  4. 2025The Challenge of Teaching Reasoning to LLMs Without RL or Distillation
  5. 2022Large Language Models Are Reasoning Teachers
  6. 2025An Empirical Study of Reasoning Steps in Thinking Code LLMs
  7. 2025Chain-of-Tools: Utilizing Massive Unseen Tools in the CoT Reasoning of Frozen Language Models
  8. 2025When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs