EVISKILL：在可重放证据中实现技能演化

中文摘要 AI 辅助

持续技能演化使LLM智能体能够在无需更新模型参数的情况下，从交互经验中积累并提炼可复用的程序性知识。其有效性不仅取决于确定要改变什么，还取决于为何改变是合理的，以及何时应成为持久性指导。然而，现有的经验驱动方法可能会丢失支持编辑的行为证据和任务上下文。此外，全局验证结果对其组成部分的变化提供了不完整的判断：局部支持的修正可能随被拒绝的修订而被丢弃，而证据可能需要更多经验来为有用的更新提供信息。为此，我们引入了EVISKILL，一个证据驱动的框架，它将执行观察组织为可重放证据卡，并合成与支持上下文有明确联系的编辑。定向重放通过重新执行来验证这些编辑，并提供修正反馈。跨轮次中，EVISKILL保留证据并暂时保留受支持的编辑以供进一步细化，而全局验证则控制其纳入最终技能。在六个LLM骨干上的三个交互基准上的实验证明了该方法的有效性。

英文摘要

Continual skill evolution enables LLM agents to accumulate and refine reusable procedural knowledge from interaction experience without updating model parameters. Its effectiveness depends on determining not only what to change, but also why a change is justified and when it should become persistent guidance. However, existing experience-driven methods can lose the behavioral evidence and task contexts supporting edits. Moreover, a global validation outcome provides an incomplete judgment of its constituent changes: locally supported corrections may be discarded with a rejected revision, while evidence may require further experience to inform useful updates. To this end, we introduce EVISKILL, an evidence-driven framework that organizes execution observations into Replayable Evidence Cards and synthesizes edits with explicit links to their supporting contexts. Targeted replay verifies these edits through re-execution and provides feedback for correction. Across epochs, EVISKILL preserves evidence and provisionally retains supported edits for further refinement, while global validation governs their incorporation into the final skill. Experiments on three interactive benchmarks across six LLM backbones demonstrate the effectiveness of this approach.

发表机构

• School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）

机构由 AI 辅助整理，请以论文原文为准。