做AI Agent开发的团队常手工写技能文档但效果有限，SkillOpt用优化器自动迭代技能文件，零推理开销且效果显著，值得尝试。
微软研究院提出SkillOpt方法，将Agent的技能文档视为可训练的外部状态，通过一个优化器模型对技能文件进行验证驱动的编辑（增、删、改指令），而Agent本身保持不变。实验显示，SkillOpt在52个（模型、基准、框架）组合中表现最佳或持平，在GPT-5.5上直接聊天提升23.5分，Codex提升24.8分，Claude Code提升19.1分，且优于人类编写的技能、TextGrad等方法。该方法不增加推理成本，学到的技能可跨模型和框架迁移。
Paper info here: https://t.co/OKHdAoGz46
Paper info here: x.com/omarsar0/statu… elvis @omarsar0 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 🔗 View Quoted Tweet 💬 1 🔄 0 ❤️ 0 👀 442 📊 1 ⚡