用多个角色辩论提升大模型推理能力，避免自我重复错误。
MAR:Multi-Agent Reflexion Improves Reasoning Abilities in LLMs
- 让多个角色扮演者互相辩论，生成更丰富的反思意见。
- 在HotPot QA上达到47%准确率，优于单个模型反思。
- 适合需要深度推理的复杂任务，如编程与问答。
大语言模型通过反思自身错误可提升推理表现，但单一模型反复自省易陷入思维僵化，不断重复相同错误。为此，本文引入多角色辩论机制，让多个具有不同人格的代理进行交互式讨论以生成反思。实验表明，该方法显著提升了反思内容的多样性。在HotPot QA任务中，模型准确率达到47% EM；在HumanEval编程评测中，准确率达82.7%，均超越单模型自反思方案。
原文摘要 · Abstract (English)
LLMs have shown the capacity to improve their performance on reasoning tasks through reflecting on their mistakes, and acting with these reflections in mind. However, continual reflections of the same LLM onto itself exhibit degeneration of thought, where the LLM continues to repeat the same errors again and again even with the knowledge that its wrong. To address this problem, we instead introduce multi-agent with multi-persona debators as the method to generate reflections. Through out extensive experimentation, we've found that the leads to better diversity of in the reflections generated by the llm agent. We demonstrate an accuracy of 47% EM HotPot QA (question answering) and 82.7% on HumanEval (programming), both performances surpassing reflection with a single llm.
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。