让多智能体系统学会自我优化，通过文本反馈持续改进决策能力。
Learning to Evolve: A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimization
- 将多智能体系统建模为可优化的文本参数图，节点包括智能体、工具和流程。
- 基于执行日志生成结构化自然语言反馈，精准定位失败并提出修改建议。
- 采用元学习策略从历史经验中学习优化方法，实现自我进化能力。
设计与优化多智能体系统（MAS）是一项复杂且耗时的“智能体工程”任务。现有自动优化方法主要聚焦于扁平提示调优，缺乏对智能体间交互关系的结构感知，且优化器本身是静态的，无法从经验中学习以改进自身策略。为此，我们提出文本参数图优化（TPGO）框架，使多智能体系统具备自我演进能力。TPGO首先将MAS建模为文本参数图（TPG），其中智能体、工具和工作流作为模块化、可优化的节点。通过分析执行轨迹，我们生成“文本梯度”——结构化的自然语言反馈，用于定位故障并建议细粒度修改。框架核心是群体相对智能体优化（GRAO），一种新型元学习策略，能够从历史优化经验中学习。通过分析过往成功与失败案例，GRAO逐步提升优化建议的有效性，使系统学会如何自我优化。在GAIA和MCP-Universe等复杂基准测试中，TPGO显著提升了当前最先进智能体框架的表现，实现了更高的成功率，验证了其自动化、自适应优化的优越性。
原文摘要 · Abstract (English)
Designing and optimizing multi-agent systems (MAS) is a complex, labor-intensive process of "Agent Engineering." Existing automatic optimization methods, primarily focused on flat prompt tuning, lack the structural awareness to debug the intricate web of interactions in MAS. More critically, these optimizers are static; they do not learn from experience to improve their own optimization strategies. To address these gaps, we introduce Textual Parameter Graph Optimization (TPGO), a framework that enables a multi-agent system to learn to evolve. TPGO first models the MAS as a Textual Parameter Graph (TPG), where agents, tools, and workflows are modular, optimizable nodes. To guide evolution, we derive "textual gradients," structured natural language feedback from execution traces, to pinpoint failures and suggest granular modifications. The core of our framework is Group Relative Agent Optimization (GRAO), a novel meta-learning strategy that learns from historical optimization experiences. By analyzing past successes and failures, GRAO becomes progressively better at proposing effective updates, allowing the system to learn how to optimize itself. Extensive experiments on complex benchmarks like GAIA and MCP-Universe show that TPGO significantly enhances the performance of state-of-the-art agent frameworks, achieving higher success rates through automated, self-improving optimization.
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。