ReAct: Synergizing Reasoning and Acting in Language Models – Google AI Blog

Posted by Shunyu Yao, Student Researcher, and Yuan Cao, Research Scientist, Google Research, Brain Team Recent advances have expanded the applicability of language models (LM) to downstream tasks. On one hand, existing language models that are properly prompted, via chain-of-thought, demonstrate emergent capabilities that carry out self-conditioned reasoning traces to derive answers from questions, excelling at various arithmetic, commonsense, and symbolic reasoning tasks. However, with chain-of-thought prompting, a model is not grounded in the external world and uses its own internal representations to generate reasoning traces, limiting its ability to reactively explore and reason or update its knowledge. On the other hand, recent work uses pre-trained language models for planning and acting in various interactive environments (e.g., text games, web navigation, embodied tasks, robotics), with a focus on mapping text contexts to text actions via the language model’s internal knowledge

ReAct: Synergizing Reasoning and Acting in Language Models Skip to main content ReAct: Synergizing Reasoning and Acting in Language Models November 8, 2022 Posted by Shunyu Yao, Student Researcher, and Yuan Cao, Research Scientist, Google Research, Brain Team Quick links Share Copy link × --> Recent advances have expanded the applicability of language models (LM) to downstream tasks. On one hand, existing language models that are properly prompted, via chain-of-thought , demonstrate emergent capabilities that carry out self-conditioned reasoning traces to derive answers from questions, excelli

saved by

• Michelle Qin

related reading

• Tracing the thoughts of a large language model \ Anthropicanthropic.com
• DeepSeek-R1arxiv.org
• [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
• Explore | alphaXivalphaxiv.org
• Language Models can Solve Computer Tasksarxiv.org
• the-illusion-of-thinking.pdfml-site.cdn-apple.com
• Language Models Perform Reasoning via Chain of Thoughtai.googleblog.com
• Language Models, World Models, and Human Model-Buildinglingo.csail.mit.edu
• Externalized reasoning oversight: a research direction for language model alignment — AI Alignment Forumalignmentforum.org
• Reasoning as Trajectoriesslhleosun.github.io
• [2201.07207] Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentsarxiv.org
• [2502.19402] General Reasoning Requires Learning to Reason from the Get-goar5iv.labs.arxiv.org