SkillsVote：智能体技能从收集、推荐到演化的生命周期治理

摘要

长时程LLM智能体留下的轨迹可作为可复用的经验，但原始轨迹噪声大且难以管理。我们将代理技能视为一种经验模式，它整合了可执行脚本与非可执行的程序性指导。然而，开放的技能生态系统中存在冗余、参差不齐且对环境敏感的工件，不加区分地更新可能污染未来的上下文。我们提出SkillsVote——一个覆盖从收集、推荐到演进的代理技能全生命周期治理框架。SkillsVote对百万级规模的开源语料库进行环境需求、质量和可验证性分析，进而为可验证技能合成任务。执行前，SkillsVote通过结构化技能库执行智能体式库搜索，以提供指导性技能上下文。执行后，它将轨迹分解为技能关联的子任务，将结果归因于技能使用、智能体探索、环境及结果信号，仅允许成功且可复现的发现进入经证据验证的更新流程。在评估中，离线演进使GPT-5.2在Terminal-Bench 2.0上提升高达7.9个百分点，在线演进使SWE-Bench Pro提升高达2.6个百分点。总体而言，当系统控制暴露、归因与保存时，受治理的外部技能库可在不更新模型的情况下改进冻结的智能体。

English

Long-horizon LLM agents leave traces that could become reusable experience, but raw trajectories are noisy and hard to govern. We treat Agent Skills as an experience schema that couples executable scripts, with non-executable guidance on procedures. Yet open skill ecosystems contain redundant, uneven, environment-sensitive artifacts, and indiscriminate updates can pollute future context. We present SkillsVote, a lifecycle-governance framework for Agent Skills from collection and recommendation to evolution. SkillsVote profiles a million-scale open-source corpus for environment requirements, quality, and verifiability, then synthesizes tasks for verifiable skills. Before execution, SkillsVote performs agentic library search over structured skill library to expose instructional skill context. After execution, it decomposes trajectories into skill-linked subtasks, attributes outcomes to skill use, agent exploration, environment, and result signals, and admits only successful reusable discoveries to evidence-gated updates. In our evaluation, offline evolution improves GPT-5.2 on Terminal-Bench 2.0 by up to 7.9 pp, while online evolution improves SWE-Bench Pro by up to 2.6 pp. Overall, governed external skill libraries can improve frozen agents without model updates when systems control exposure, credit, and preservation.