ReAct: Synergizing Reasoning and Acting in Language Models

This paper introduces ReAct, an approach that integrates reasoning and acting in large language models (LLMs). ReAct enables LLMs to generate both reasoning traces and task-specific actions in an interleaved manner. This synergy allows reasoning to help induce, track, and update action plans, while actions interface with external sources like knowledge bases to gather more information, overcoming issues of hallucination and error propagation in prior methods.

Visit Website

Introduction

Back

Information

Websitearxiv.org
AuthorsShunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, Yuan Cao
Published date2022/10/06

More Items

SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering

2024

John Yang, Carlos E. Jimenez +5

SWE-agent is a system designed to empower language model (LM) agents to autonomously perform software engineering tasks. It features a custom agent-computer interface (ACI) that enhances the agent's ability to navigate repositories, create and edit code, and execute programs, achieving state-of-the-art results on the SWE-bench and HumanEvalFix benchmarks. [2, 5, 8]

paper ai-agent LLM ai-coding engineering

Relational recurrent neural networks

2018

Adam Santoro, Ryan Faulkner +8

This paper introduces a Relational Memory Core that embeds multi-head dot-product attention into recurrent memory to enable explicit relational reasoning. Evaluated on synthetic distance-sorting, program execution, partially-observable reinforcement learning and large-scale language-modeling benchmarks, it consistently outperforms LSTM and memory-augmented baselines, setting state-of-the-art results on WikiText-103, Project Gutenberg and GigaWord. By letting memories interact rather than merely store information, the approach substantially boosts sequential relational reasoning and downstream task performance.

foundation 30u30 paper NLP LLM

Neural Machine Translation by Jointly Learning to Align and Translate

2014

Dzmitry Bahdanau, Kyunghyun Cho +1

This paper introduces an attention-based encoder–decoder NMT architecture that learns soft alignments between source and target words while translating, eliminating the fixed-length bottleneck of earlier seq2seq models. The approach substantially improves BLEU, especially on long sentences, and matches phrase-based SMT on English-French without additional hand-engineered features. The attention mechanism it proposes became the foundation for virtually all subsequent NMT systems and inspired attention-centric models like the Transformer, reshaping machine translation and sequence modeling across NLP.

30u30 paper NLP translation

While large language models (LLMs) have shown impressive abilities, their capacities for reasoning (like chain-of-thought) and acting (like action plan generation) have been studied separately. This paper proposes ReAct, a new paradigm where LLMs generate both reasoning traces and task-specific actions in an interleaved fashion.

This approach creates a powerful synergy:

Reasoning helps the model to create, track, and update action plans, as well as handle exceptions.
Acting allows the model to connect with external sources, such as a Wikipedia API, to gather additional information and ground its reasoning.

The ReAct framework was tested on a variety of language and decision-making tasks. In question answering (HotpotQA) and fact verification (Fever), it successfully mitigates issues of hallucination and error propagation common in chain-of-thought models. On interactive decision-making benchmarks like ALFWorld and WebShop, ReAct significantly outperformed imitation and reinforcement learning methods. The resulting task-solving trajectories are more human-like, interpretable, and trustworthy.