CoEvol: Constructing Better Responses for Instruction Finetuning through Multi-Agent Cooperation

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 multiagent cooperation framework for the improvement of responses for instructions. To effectively refine the responses, we develop an iterative framework following a debate-adviseedit-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 Al-pacaEval, demonstrating its effectiveness in enhancing instruction-following capabilities for LLMs. 1 * Equal contribution. † Under the Joint Ph.D. Program between UM and SIAT.