GraphSkillEvo：图结构智能体技能的进化优化

中文摘要 AI 辅助

技能可以通过提供特定于任务的过程性指导来提升大型语言模型（LLM）智能体的性能，而技能优化则通过迭代改进进一步增强其有效性。然而，现有的技能优化方法通常将技能表示为非结构化的自然语言指令，这带来了两个关键挑战：1）非结构化技能往往缺乏明确的工作流级指导，且包含大量冗余，使得LLM难以执行；2）无约束自然语言技能的庞大搜索空间使得技能优化效率低下。为解决这些挑战，我们提出将技能表示为图结构的自然语言工件。在图结构技能中，每个节点代表一个执行步骤及其操作指导，而有向边则编码步骤之间依赖于上下文的转换。与非结构化技能相比，图结构技能能够提供清晰的工作流级指导。此外，所提出的图结构技能还能促进技能优化。基于这种结构化表示，我们引入了GraphSkillEvo，一个基于种群的进化优化框架，包含针对图结构技能的变异和交叉算子。通过维护多个候选技能并组合有效组件，GraphSkillEvo能够在结构化技能空间中进行比纯基于LLM的迭代自我改进更广泛、更全面的探索。在五个智能体基准上的大量实验表明，GraphSkillEvo持续优于强大的技能优化基线SkillOpt，在GPT-5.4-nano上平均准确率提高了4.01%，在GPT-5.4上提高了1.76%。我们的代码可在以下网址获取：此https URL。

英文摘要

Skills can improve the performance of Large Language Model (LLM) agents by providing task-specific procedural guidance, while skill optimization further improves their effectiveness through iterative refinement. However, existing skill optimization methods typically represent skills as unstructured natural-language instructions, creating two key challenges: 1) Unstructured skills often lack explicit workflow-level guidance and contain substantial redundancy, making them difficult for LLMs to execute; 2) the vast search space of unconstrained natural-language skills makes skill optimization ineffective. To address these challenges, we propose representing skills as graph-structured natural-language artifacts. In graph-structured skills, each node represents an execution step together with its operational guidance, while directed edges encode context-dependent transitions between steps. Compared to unstructured skills, graph-structured skills can provide clear workflow-level guidance. Moreover, the proposed graph-structured skill can also facilitate skill optimization. Building on this structured representation, we introduce GraphSkillEvo, a population-based evolutionary optimization framework with mutation and crossover operators for graph-structured skills. By maintaining multiple candidate skills and combining effective components, GraphSkillEvo enables broader and more comprehensive exploration of the structured skill space than purely LLM-based iterative self-refinement. Extensive experiments across five agent benchmarks demonstrate that GraphSkillEvo consistently outperforms the strong skill optimization baseline SkillOpt, improving average accuracy by 4.01% on GPT-5.4-nano and 1.76% on GPT-5.4. Our code is available at https://github.com/ruisun7/GraphSkillEvo.

发表机构

• City University of Hong Kong（香港城市大学）
• National University of Singapore（新加坡国立大学）
• Southern University of Science and Technology（南方科技大学）

机构由 AI 辅助整理，请以论文原文为准。