WikiSkill：将智能体经验编译为持久知识以实现技能演化
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
- Google Research（谷歌研究院）
- Virginia Tech（弗吉尼亚理工大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
WikiSkill是使智能体技能与持久知识库协同演化的框架，在多基准与模型上优于现有方法，证实持久知识积累对技能演化关键，且演化技能可跨模型迁移。
AI中文摘要：
智能体技能将专业知识与工作流打包为可复用资源，以扩展AI智能体的能力。近期研究可从智能体经验中自动发现此类技能，使智能体能通过交互逐步适应。然而，指导技能开发的见解通常分散在优化历史中，限制了其在迭代间的系统复用。我们提出WikiSkill，这是一种使智能体技能与持久知识库（wiki）协同演化的框架。总体而言，WikiSkill将原始执行经验、累积知识与可执行技能分离，同时持续将经验整合到wiki中，后续的技能更新可基于此开展。在各类基准测试与模型上，WikiSkill始终优于当前最先进的技能演化方法，且在多数模型-基准测试设置中优于无技能基线。我们发现技能演化与模型扩展互补：更大规模的模型通常从演化技能中受益更多，而具备技能的较小模型可显著超越无技能的更大模型。我们还发现演化技能可在模型及模型家族间有效迁移，其他模型演化出的技能可优于自演化技能。最后， ablation研究（消融研究）证实，wiki中的持久知识积累对有效技能演化至关重要。这些结果表明，系统地积累与优化智能体经验，对开发可复用且可迁移的技能具有重要意义。
英文摘要：
Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. Recent work automatically discovers such skills from agent experience, which enables agents to progressively adapt through interaction. However, the insights that guide skill development typically remain scattered across optimization histories, limiting their systematic reuse across iterations. We introduce WikiSkill, a framework that co-evolves agent skills with a persistent knowledge base (wiki). At a high level, WikiSkill separates raw execution experience, accumulated knowledge, and executable skills, while continuously consolidating experience into the wiki, which subsequent skill updates can build on. Across diverse benchmarks and models, WikiSkill consistently outperforms state-of-the-art skill-evolution methods and improves over no-skill baselines in most model-benchmark settings. We find that skill evolution complements model scaling: larger models generally benefit more from evolved skills, while smaller models with skills can outperform substantially larger models without them. We also find that evolved skills transfer effectively across models and model families, and skills evolved by other models can outperform self-evolved skills. Finally, our ablation studies confirm that persistent knowledge accumulation in the wiki is critical for effective skill evolution. These results demonstrate the benefits of systematically accumulating and refining agent experience for developing reusable and transferable skills.
