mlsanityData to 14 Oct 2026

ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models

arXiv 2305.14323 ↗First posted 23 May 2023cs.CLcited by 43

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Although large language models (LLMs) have achieved excellent performance in a variety of evaluation benchmarks, they still struggle in complex reasoning tasks which require specific knowledge and multi-hop reasoning. To improve the reasoning abilities, we propose ChatCoT, a tool-augmented chain-of-thought reasoning framework for chat-based LLMs (e.g., ChatGPT). In ChatCoT, we model the chain-of-thought (CoT) reasoning as multi-turn conversations, to utilize tools in a more natural way through chatting. At each turn, LLMs can either interact with tools or perform the reasoning. Our approach can effectively leverage the multi-turn conversation ability of chat-based LLMs, and integrate the thought chain following and tools manipulation in a unified way. Specially, we initialize the early turns of the conversation by the knowledge about tools, tasks, and reasoning format, and propose an iterative tool-augmented reasoning step to perform step-by-step tool-augmented reasoning. The experiment results on two complex reasoning datasets (MATH and HotpotQA) have shown the effectiveness of ChatCoT on complex reasoning tasks, achieving a 7.9% relative improvement over the state-of-the-art baseline. Our code and data are available at: urlhttps://github.com/RUCAIBOX/ChatCoT.

Key facts. Cited by 43 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 3 of its 48 references that are in the map. First posted on arXiv 23 May 2023.

Builds on

3 of 48 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Data16 May
  2. 2023Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models19 Apr

Other references · 1

  1. 2023ART: Automatic multi-step reasoning and tool-use for large language modelscited by 197

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 9; 2024: 16; 2025: 14; 2026: 4.

43 papers.

Sort:

By area:

  1. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  2. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  3. 2024Tool Learning with Large Language Models: A Surveycited by 223
  4. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 212
  5. 2025Agentic Reinforced Policy Optimizationcited by 172
  6. 2024Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospectscited by 132
  7. 2025A Survey of Context Engineering for Large Language Modelscited by 126
  8. 2024A Review of Large Language Models and Autonomous Agents in Chemistrycited by 99
  9. 2024Demystifying Chains, Trees, and Graphs of Thoughtscited by 63
  10. 2024LLM With Tools: A Surveycited by 61
  11. 2023TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usagecited by 55
  12. 2023Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoningcited by 49
31 more
  1. 2025Continuum: Efficient and Robust Multi-Turn LLM Agent Scheduling with KV Cache Time-to-Livecited by 44
  2. 2023TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Systemscited by 39
  3. 2025Generative to Agentic AI: Survey, Conceptualization, and Challengescited by 33
  4. 2025Plan and Budget: Effective and Efficient Test-Time Scaling on Reasoning Large Language Modelscited by 32
  5. 2023An In-depth Survey of Large Language Model-based Artificial Intelligence Agentscited by 31
  6. 2024TOOLVERIFIER: Generalization to New Tools via Self-Verificationcited by 24
  7. 2024Word-Sequence Entropy: Towards Uncertainty Estimation in Free-Form Medical Question Answering Applications and Beyondcited by 18
  8. 2023GEAR: Augmenting Language Models with Generalizable and Efficient Tool Resolutioncited by 17
  9. 2024CausalEval: Towards Better Causal Reasoning in Language Modelscited by 13
  10. 2024Uncertainty Estimation of Large Language Models in Medical Question Answeringcited by 10
  11. 2025MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problemscited by 10
  12. 2025LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systemscited by 10
  13. 2025A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directionscited by 9
  14. 2025Hell or High Water: Evaluating Agentic Recovery from External Failurescited by 9
  15. 2025Conformal Information Pursuit for Interactively Guiding Large Language Modelscited by 7
  16. 2023DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Textcited by 5
  17. 2024DCR: Divide-and-Conquer Reasoning for Multi-choice Question Answering with LLMscited by 5
  18. 2025GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chainingcited by 5
  19. 2026Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model Agentscited by 5
  20. 2024ITCMA: A Generative Agent Based on a Computational Consciousness Structurecited by 3
  21. 2024ROMAS: A Role-Based Multi-Agent System for Database monitoring and Planningcited by 3
  22. 2025Test-Time Policy Adaptation for Enhanced Multi-Turn Interactions with LLMscited by 3
  23. 2023Furthest Reasoning with Plan Assessment: Stable Reasoning Path with Retrieval-Augmented Large Language Modelscited by 2
  24. 2024SEAL: Suite for Evaluating API-use of LLMscited by 2
  25. 2024Language hooks: a modular framework for augmenting LLM reasoning that decouples tool usage from the model and its promptcited by 2
  26. 2024RE-GAINS & EnChAnT: Intelligent Tool Manipulation Systems For Enhanced Query Responsescited by 1
  27. 2025SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphscited by 1
  28. 2025A Multi-Agent Probabilistic Inference Framework Inspired by Kairanban-Style CoT System with IdoBata Conversation for Debiasingcited by 0
  29. 2026A Taxonomy of Cognitive Capability Gaps in Generative and Agentic AIcited by 0
  30. 2026Towards Robust Tool Use in Agents via Experience-Driven Adaptive Guidancecited by 0
  31. 2026Clueing up LLMs with Tool-Augmented Deductive Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance
  2. 2023DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models
  3. 2025Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
  4. 2025Fast, Slow, and Tool-augmented Thinking for LLMs: A Review
  5. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approaches
  6. 2024ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting
  7. 2026The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes
  8. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models