改进ReAct模型，让大模型更专注、不循环，答题更快更准。
Focused ReAct: Improving ReAct through Reiterate and Early Stop
- 引入重述和早停机制，避免偏离问题和重复动作。
- 准确率提升18%至530%，运行时间最多减少34%。
- 适合需要高精度与高效推理的复杂任务场景。
大型语言模型（LLMs）在推理和决策能力上显著提升，如ReAct方法所示。然而，尽管ReAct在处理复杂任务时表现良好，仍面临两大挑战：容易偏离原始问题以及陷入动作循环。为解决这些问题，我们提出改进版的聚焦式ReAct（Focused ReAct），引入重述和早停机制，帮助模型保持对原始查询的关注，避免重复行为。实验结果显示，相较于原始ReAct方法，准确率提升18%至530%，运行时间最多减少34%。
原文摘要 · Abstract (English)
Large language models (LLMs) have significantly improved their reasoning and decision-making capabilities, as seen in methods like ReAct. However, despite its effectiveness in tackling complex tasks, ReAct faces two main challenges: losing focus on the original question and becoming stuck in action loops. To address these issues, we introduce Focused ReAct, an enhanced version of the ReAct paradigm that incorporates reiteration and early stop mechanisms. These improvements help the model stay focused on the original query and avoid repetitive behaviors. Experimental results show accuracy gains of 18% to 530% and a runtime reduction of up to 34% compared to the original ReAct method.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。