做智能体开发的工程师别再手写技能文档了——SkillOpt 证明自动优化技能文件能带来显著性能提升，且零推理开销，值得在你的 Agent 工作流中尝试。
微软研究院提出 SkillOpt，一种将智能体技能文档视为可训练外部状态的新方法。该方法通过一个优化器模型对技能文件进行验证门控的增删改编辑，并引入文本学习率控制改写强度，而智能体本身保持不变。在 52 个（模型、基准、工具）组合上，SkillOpt 均达到最佳或并列最佳，在 GPT-5.5 上直接聊天提升 23.5 点，与 Codex 配合提升 24.8 点，与 Claude Code 配合提升 19.1 点，且零额外推理成本。学到的技能可跨模型和工具迁移，效果优于人工编写技能、TextGrad、GEPA 和 EvoSkill。
New research from Microsoft Research I see a lot of AI engineers handwriting agent skill docs and h...
New research from Microsoft Research I see a lot of AI engineers handwriting agent skill docs and hope they generalize. Probably not optimal. This works show why. It treats the skill doc as a trainable external state of a frozen agent instead. It introduces SkillOpt, where an optimizer model makes validation-gated edits to the skill file. It adds, deletes, or replaces instructions, with a textual learning rate that controls how aggressively each round rewrites the doc. The agent itself never changes. SkillOpt is best or tied on all 52 (model, benchmark, harness) cells. On GPT-5.5 it adds 23.5 points in direct chat, 24.8 with Codex, and 19.1 with Claude Code over no skill. It beats human-written skills, TextGrad, GEPA, and EvoSkill, carries zero extra inference-time cost, and the learned skills transfer across models and harnesses. Paper: arxiv.org/abs/2605.23904 Learn to build effective AI agents in our academy: academy.dair.ai 💬 8 🔄 23 ❤️ 109 👀 9147 📊 43 ⚡