让多个AI-agent的提示词自动协同优化，提升整体任务表现。
MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems
- 通过联合评估机制，根据后续代理的成功率优化提示词。
- 在6个任务中平均准确率提升2.9个百分点。
- 适合需要多智能体协作的复杂任务研究者使用。
基于大语言模型（LLM）的多智能体系统（MAS）在解决复杂协作任务方面展现出潜力，其中智能体通常通过角色特定的提示词进行协调。尽管提示词质量至关重要，但跨交互智能体联合优化提示词仍具挑战性，主要源于局部目标与全局系统目标之间的不一致。为此，我们提出MASPO，一种可自动迭代优化整个系统提示词的新框架。其核心创新在于联合评估机制，该机制不仅评估提示词的局部有效性，更关注其对后续智能体下游成功的影响，从而在无需真实标签的情况下弥合局部交互与全局结果间的差距。此外，MASPO采用数据驱动的进化束搜索，高效探索高维提示空间。在6个不同任务上的大量实证评估表明，MASPO始终优于现有最佳提示优化方法，平均准确率提升2.9。代码已公开于https://github.com/wangzx1219/MASPO。
原文摘要 · Abstract (English)
Large language model (LLM)-based Multi-agent systems (MAS) have shown promise in tackling complex collaborative tasks, where agents are typically orchestrated via role-specific prompts. While the quality of these prompts is pivotal, jointly optimizing them across interacting agents remains a non-trivial challenge, primarily due to the misalignment between local agent objectives and holistic system goals. To address this, we introduce MASPO, a novel framework designed to automatically and iteratively refine prompts across the entire system. A core innovation of MASPO is its joint evaluation mechanism, which assesses prompts not merely by their local validity, but by their capacity to facilitate downstream success for successor agents. This effectively bridges the gap between local interactions and global outcomes without relying on ground-truth labels. Furthermore, MASPO employs a data-driven evolutionary beam search to efficiently navigate the high-dimensional prompt space. Extensive empirical evaluations across 6 diverse tasks demonstrate that MASPO consistently outperforms state-of-the-art prompt optimization methods, achieving an average accuracy improvement of 2.9. We release our code at https://github.com/wangzx1219/MASPO.
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。