SkillEvo：来自多轮交互反馈的自我更新演化梯度

摘要

智能体技能目前要么由人工编写，要么通过单次大语言模型生成过程产生，因此缺乏闭环机制，无法从它们实际引发的交互失败中改进。近期研究确实弥补了这一闭环，但其反馈来源于单轮问答评估。其后果是严重的不对称性：一旦第一轮修改修补了单次交换所能揭示的缺口，演化梯度便会衰减，仅在多轮交互中浮现的缺陷依然不可见，演化进程随之停滞。这些系统中的治理机制同样由端到端验证分数驱动——这是一种标量门控，能够拒绝退化候选体，却既无法定位其结构性原因，也无法加以修复。我们认为，制约技能持续演化的关键因素既不是编辑能力，也不是迭代次数，而是评估反馈能否持续提供可信的演化梯度。我们提出SkillEvo，其中可信反馈生成梯度，可控治理约束其方向。第一个组件将多轮用户模拟从评估端点重构为反馈生成器：后续问题层层暴露缺陷，使得每一轮修订既消耗反馈，又产生新反馈。第二个组件以独立治理层取代标量门控的被动拒绝，主动修复事实性退化和结构臃肿，从而防止梯度随着退化累积而漂移。在六类云服务、9个生产技能和98个技能参考文件上，SkillEvo分别超过基于自我反思的演化23.0分，以及单轮问答驱动的演化15.4分。

English

Agent Skills are today either hand-authored or produced in a single LLM generation pass, and consequently possess no closed loop through which they might improve from the interaction failures they actually cause. Recent work does close this loop, but derives its feedback from single-turn question-answering evaluation. The consequence is a sharp asymmetry: once the first round has patched the gaps that a single exchange can reveal, the evolution gradient decays, the defects that surface only across multiple turns remain invisible, and evolution stalls. Governance in these systems is likewise driven by an end-to-end verification score, a scalar gate that can reject a degraded candidate but can neither localize nor repair its structural cause. We argue that the binding constraint on sustained skill evolution is neither editing capability nor the number of iterations, but whether the evaluation feedback keeps supplying trustworthy evolution gradients. We introduce SkillEvo, in which trustworthy feedback generates the gradient and controllable governance constrains its direction. The first component recasts multi-turn user simulation from an evaluation endpoint into a feedback generator: follow-up questions expose defects layer by layer, so that every round of revision both consumes feedback and produces new feedback. The second replaces the passive rejection of a scalar gate with an independent governance layer that actively repairs factual degradation and structural bloat, preventing the gradient from drifting as degradation accumulates. Across six categories of cloud services, 9 production Skills, and 98 skill-reference files, SkillEvo surpasses self-reflection-based evolution by 23.0 points and single- turn-QA-driven evolution by 15.4 points.