一行代码让AI自己进化技能
AI智能体（比如写代码的Copilot）的技能优化通常需要复杂流程，但这篇论文发现：你只需要给AI一句“氛围描述”（vibe），它就能自己迭代改进。研究者把技能优化形式化为零阶优化，并提炼出三个核心原则：基于文件系统的轨迹探索、共识属性挖掘、独立验证门控。去掉所有冗余后，他们的方法SkillOpt-Lite不仅更快，效果还更好——在数学任务上，小模型GPT-5.4-nano用此方法甚至超过了标准流程下的大模型GPT-5.5。更酷的是，他们把整个框架集成到了VSCode Copilot里，开发者只需写一行提示就能让智能体自我进化。这不是你明天就能直接用的功能，但它展示了AI自我优化的极简路径：把智能体所有组件当作普通可编辑代码，让进化变得像写代码一样自然。
📄 原文摘要(英文)
While skill optimization for autonomous agents has gained traction, existing methods rely on complex pipelines. This leaves a fundamental question unaddressed: What constitutes a minimal viable pipeline for skill optimization, where every component is justified by theory or empirical necessity? We formalize skill optimization via Zeroth-Order (ZO) optimization, mapping classical counterparts (central difference, trust regions) to recent literature. Noting that unlike blind numerical perturbations in classical ZO, skill trajectories serve as interpretable debugging feedback. Grounded in Claude Code philosophy and PAC learning, we establish three principles for convergence and generalization: file-system-based trajectory exploration, consensus attribute mining, and independent validation gating. Eliminating redundancies, we propose SkillOpt-Lite. It accelerates convergence and outperforms full SkillOpt: improving LiveMath by +8.8 points on GPT-5.5 and +25.4 points on GPT-5.4-nano, allowing the nano model to surpass standard GPT-5.4 optimized by SkillOpt. Finally, we integrate our framework into production coding agents like VSCode Copilot, enabling developers to evolve agent skills via one line of vibe. Because our framework treats all agent components simply as standard editable code, this minimal pipeline naturally generalizes to full harness optimization (HarnessOpt). On SpreadsheetBench, HarnessOpt enables GPT-5.4-nano to achieve 0.7758 accuracy, outperforming the larger GPT-5.5 running standard pipelines (0.7620). Code is available at https://github.com/EvolvingLMMs-Lab/SkillOpt-Lite.