CoEvol：通过多智能体协作为指令微调构建更优回复
CoEvol: Constructing Better Responses for Instruction Finetuning through Multi-Agent Cooperation
AI总结：
本文提出CoEvol多智能体协作框架，通过辩论—建议—编辑—评判迭代流程和两阶段辩论策略改进IFT回复质量，并在MT-Bench与AlpacaEval上验证其有效性。
摘要：
近年来，面向大语言模型（LLM）的指令微调（IFT）受到广泛关注，用于提升模型在未见任务上的性能。已有研究尝试自动构建并有效筛选IFT数据。然而，我们认为以往方法尚未充分利用LLM在提升数据质量方面的潜力；IFT数据中的回复仍可借助LLM自身能力进一步增强。本文提出CoEvol，这是一个基于LLM的多智能体协作框架，用于改进指令回复。为有效精炼回复，我们遵循“辩论—建议—编辑—评判”范式开发了一个迭代框架，并进一步设计了两阶段多智能体辩论策略，以确保框架内编辑建议的多样性与可靠性。实验表明，配备CoEvol的模型在MT-Bench和AlpacaEval评测中优于具有竞争力的基线，证明了其在增强LLM指令遵循能力方面的有效性。
英文摘要：
In recent years, instruction fine-tuning (IFT) on large language models (LLMs) has garnered considerable attention to enhance model performance on unseen tasks. Attempts have been made on automatic construction and effective selection for IFT data. However, we posit that previous methods have not fully harnessed the potential of LLMs for enhancing data quality. The responses within IFT data could be further enhanced by leveraging the capabilities of LLMs themselves. In this paper, we propose CoEvol, an LLM-based multi-agent cooperation framework for the improvement of responses to instructions. To effectively refine the responses, we develop an iterative framework following a debate-advise-edit-judge paradigm. A two-stage multi-agent debate strategy is further devised to ensure the diversity and reliability of editing suggestions within the framework. Empirically, models equipped with CoEvol outperform competitive baselines evaluated by MT-Bench and AlpacaEval, demonstrating its effectiveness in enhancing instruction-following capabilities for LLMs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
