ReAct: Synergizing Reasoning and Acting in Language Models. (cf LLM)

Language models are getting better at reasoning (e.g. chain-of-thought prompting) and acting (e.g. WebGPT, SayCan, ACT-1), but these two directions have remained separate. ReAct asks, what if these two fundamental capabilities are combined?

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

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

ReAct: Synergizing Reasoning and Acting in Language Models, from Google Research, Brain Team.

existing language models (LLM) 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

While actions lead to observation feedback from an external environment (“Env” in the figure below), reasoning traces do not affect the external environment. Instead, they affect the internal state of the model by reasoning over the context and updating it with useful information to support future reasoning and acting.

Language Models Perform Reasoning via Chain of Thought

Posted by Jason Wei and Denny Zhou, Research Scientists, Google Research, Brain team

Even the largest language models, however, can still struggle with certain multi-step reasoning tasks, such as math word problems and commonsense reasoning. How might we enable language models to perform such reasoning tasks?

In “Chain of Thought Prompting Elicits Reasoning in Large Language Models,” we explore a prompting method for improving the reasoning abilities of language models. Called chain of thought prompting, this method enables models to decompose multi-step problems into intermediate steps

React makes it painless to create interactive UIs. Design simple views for each state in your application, and React will efficiently update and render just the right components when your data changes. aka ReactJS

Created-at and championed-by Facebook.

Esp popular because of React-Native.



Edited:    |       |    Search Twitter for discussion