AgentGrad：面向多智能体系统的干预引导提示优化
AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems
- Korea University（高丽大学）
- KAIST（韩国科学技术院）
- Meta AI
- UNIST（蔚山科学技术院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对多智能体系统提示优化中梯度提取与聚合的缺陷，提出基于顺序干预和语义文本梯度抽象的AgentGrad框架，在五个基准上达到最优性能并提速2.5倍。
AI中文摘要：
基于大型语言模型（LLM）的多智能体系统（MAS）通过采用专门化的多个智能体实现了强大的性能，但其性能依赖于每个智能体的提示设计。对于MAS提示优化，使用自然语言反馈指导提示更新的文本梯度方法已成为一种领先范式。在本文中，我们识别了现有文本梯度方法在两个阶段中的局限性：梯度提取和梯度聚合。在梯度提取阶段，先前的工作选择目标提示时未验证修改它是否能解决失败，并且在没有对相应智能体中间输出的智能体级监督的情况下推导梯度。在梯度聚合阶段，各个梯度被随机分组并拼接，常常混合不相关的失败模式，产生无法泛化的提示。为解决这些局限性，我们提出了AgentGrad，一个基于顺序干预和语义文本梯度抽象的多智能体系统提示优化框架。对于每次失败，顺序干预一次只修改一个智能体的行为，以识别其修改能解决失败的目标智能体。目标智能体的修改后输出随后作为智能体级监督，用于提取细粒度梯度。语义文本梯度抽象将语义相似的梯度聚类，以防止混合不相关的失败模式，并将每个聚类抽象为捕获共享纠正模式的广义梯度。实验结果表明，AgentGrad在五个MAS基准上实现了最先进的性能，并且与次快基线相比，平均将墙钟优化时间减少了2.5倍。
英文摘要：
Large language model (LLM)-based multi-agent systems (MAS) achieve strong performance by employing specialized multiple agents, yet their performance depends on the prompt design of each agent. For MAS prompt optimization, textual gradient methods that guide prompt updates using natural-language feedback have emerged as a leading paradigm. In this paper, we identify limitations in two stages of existing textual gradient approaches: gradient extraction and gradient aggregation. In gradient extraction, previous works select a target prompt without verifying whether modifying it resolves the failure, and derive gradients without agent-level supervision over the corresponding agent's intermediate output. In gradient aggregation, individual gradients are randomly grouped and concatenated, often mixing unrelated failure modes and producing prompts that fail to generalize. To address these limitations, we propose AgentGrad, a prompt optimization framework for multi-agent systems based on sequential intervention and semantic textual gradient abstraction. For each failure, sequential intervention modifies the behavior of one agent at a time to identify the target agent whose modification resolves the failure. The modified output of the target agent then serves as agent-level supervision for extracting a fine-grained gradient. Semantic textual gradient abstraction clusters semantically similar gradients to prevent mixing unrelated failure modes, and abstracts each cluster into a generalized gradient that captures the shared corrective pattern. Experimental results show that AgentGrad achieves state-of-the-art performance across five MAS benchmarks while reducing wall-clock optimization time by $2.5\times$ and optimization cost by 21.8\% on average compared to the next-best baselines.
