同时优化AI智能体的结构与配置，提升可靠性与效率。
Maestro: Joint Graph & Config Optimization for Reliable AI Agents
- 联合搜索模块结构与参数配置，实现全局优化。
- 在多个基准上平均超越现有方法12%以上，且用更少试运行次数。
- 适合需要修复结构性缺陷的复杂AI智能体开发场景。
构建可靠的LLM智能体需在两个层面做出决策：图结构（模块组成及信息流）和每个节点的配置（模型、提示词、工具、控制参数）。现有优化器大多仅调整配置而固定图结构，无法解决结构性失效问题。我们提出Maestro，一个框架无关的全链路优化框架，联合搜索图结构与配置，在显式回放/令牌预算约束下最大化智能体质量。除数值指标外，Maestro还利用回放轨迹中的反思性文本反馈来优先排序修改，提升样本效率并精准定位特定失败模式。在IFBench和HotpotQA基准上，Maestro持续超越主流提示优化器MIPROv2、GEPA和GEPA+Merge，平均提升12%、4.9%和4.86%；即使仅限于提示优化，仍分别领先9.65%、2.37%和2.41%。其性能提升仅需远少于GEPA的回放次数。在面试官与RAG两类应用中亦取得显著增益，表明联合图与配置搜索能有效应对仅靠提示调优无法解决的结构性缺陷。
原文摘要 · Abstract (English)
Building reliable LLM agents requires decisions at two levels: the graph (which modules exist and how information flows) and the configuration of each node (models, prompts, tools, control knobs). Most existing optimizers tune configurations while holding the graph fixed, leaving structural failure modes unaddressed. We introduce Maestro, a framework-agnostic holistic optimizer for LLM agents that jointly searches over graphs and configurations to maximize agent quality, subject to explicit rollout/token budgets. Beyond numeric metrics, Maestro leverages reflective textual feedback from traces to prioritize edits, improving sample efficiency and targeting specific failure modes. On the IFBench and HotpotQA benchmarks, Maestro consistently surpasses leading prompt optimizers--MIPROv2, GEPA, and GEPA+Merge--by an average of 12%, 4.9%, and 4.86%, respectively; even when restricted to prompt-only optimization, it still leads by 9.65%, 2.37%, and 2.41%. Maestro achieves these results with far fewer rollouts than GEPA. We further show large gains on two applications (interviewer & RAG agents), highlighting that joint graph & configuration search addresses structural failure modes that prompt tuning alone cannot fix.
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。