用契约检测大模型技能库的隐性失效，精准定位问题根源。
Skill Drift Is Contract Violation: Proactive Maintenance for LLM Agent Skill Libraries
- 将技能退化视为契约违约，通过角色相关假设验证来识别真正失效
- 在599个无漂移和强负例中零误报，真实场景下检测精度达86%
- 可自动定位故障点，修复成功率从10%提升至78%
大语言模型代理依赖可复用的技能库，但这些技能会因外部服务、包、API及配置的演变而无声退化。现有监控工具在错误粒度上检测：只关注值的变化，而非值在技能中的角色。评论中的版本号是噪声，而依赖项中的相同字符串则是操作义务。本文将技能漂移定义为契约违约，提出 sgname{}，从技能文档中提取可执行的环境契约，并仅对具有角色意义的假设进行验证。这一区分使监控从噪声中解脱，实现精准维护信号。无契约的CI探测产生40%假阳性，而 sgname{} 在599个无漂移和硬负例中零误报（威尔逊95%置信区间[0,0.6]%）。在已知漂移验证中， sgname{} 达到100%精确率与76%召回率；在49个真实技能的预注册研究中，以86%保守精确率发现实时漂移。被违反的契约还能驱动可行动修复，使单轮修复成功率从10%提升至78%。论文发布 dbname{}，一个包含880对样本的技能退化基准数据集。
原文摘要 · Abstract (English)
LLM agents increasingly rely on reusable skill libraries, but these skills silently decay as the external services, packages, APIs, and configurations they reference evolve. Existing monitors detect such changes at the wrong granularity: they observe values, not the role those values play in a skill. A version string in a comment is noise; the same string in a pinned dependency is an operational obligation. We formulate skill drift as contract violation and introduce \sgname{}, which extracts executable environment contracts from skill documents and validates only those role-bearing assumptions against known or live conditions. This distinction turns noisy monitoring into a precision-first maintenance signal. Contract-free CI probes produce 40\% false positives, while \sgname{} raises zero false alarms over 599 no-drift and hard-negative cases (Wilson 95\% CI $[0,0.6]\%$). In known-drift verification, \sgname{} achieves 100\% precision and 76\% recall with the strongest backbone; in a pre-registered study over 49 real skills, it discovers live drift with 86\% conservative precision. Violated contracts also make repair actionable, improving one-round success from 10\% without localization to 78\%. We release \dbname{}, an 880-pair benchmark for skill degradation.
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。