ReAct: Synergizing Reasoning and Acting in Language Models

By Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, Yuan Cao. International Conference on Learning Representations, 2022

8,935 citations recorded by the source corpus.

While large language models (LLMs) have demonstrated impressive capabilities across tasks in language understanding and interactive decision making, their abilities for reasoning (e.g. chain-of-thought prompting) and acting (e.g. action plan generation) have primarily been studied as separate topics. In this paper, we explore the use of LLMs to generate both reasoning traces and task-specific actions in an interleaved manner, allowing for greater synergy between the two: reasoning traces help the model induce, track, and update action plans as well as handle exceptions, while actions allow it to interface with external sources, such as knowledge bases or environments, to gather additional information. We apply our approach, named ReAct, to a diverse set of language and decision making tasks and demonstrate its effectiveness over state-of-the-art baselines, as well as improved human interpretability and trustworthiness over methods without reasoning or acting components. Concretely, on question answering (HotpotQA) and fact verification (Fever), ReAct overcomes issues of hallucination and error propagation prevalent in chain-of-thought reasoning by interacting with a simple Wikipedia API, and generates human-like task-solving trajectories that are more interpretable than baselines without reasoning traces. On two interactive decision making benchmarks (ALFWorld and WebShop), ReAct outperforms imitation and reinforcement learning methods by an absolute success rate of 34% and 10% respectively, while being prompted with only one or two in-context examples. Project site with code: https://react-lm.github.io

Subfields: Artificial Intelligence, Prompting & Reasoning, LLM Agents & Tool Use

View Paper: https://arxiv.org/abs/2210.03629

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Mohit Bansal
  2. Jianfeng Gao
  3. Percy Liang
  4. Luke S. Zettlemoyer
  5. Graham Neubig
  6. Yejin Choi
  7. Quoc V. Le
  8. Yoshua Bengio

In Prompting & Reasoning

  1. Luke S. Zettlemoyer
  2. Minlie Huang
  3. Denny Zhou
  4. Zhiyuan Liu
  5. Mohit Bansal
  6. Michael Lewis
  7. Tushar Khot
  8. Ashish Sabharwal

In LLM Agents & Tool Use

  1. Stephen Marcus McAleer
  2. Pierre Baldi
  3. Geunwoo Kim
  4. Andy Zeng
  5. Aleksandra Faust
  6. Izzeddin Gur
  7. Percy Liang
  8. Timothy P. Lillicrap

Citations in the corpus