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，最简方案反而更强。研究者把技能优化形式化为“零阶优化”，核心是三条原则：用文件系统记录轨迹、挖掘共识属性、独立验证把关。结果，一个超小模型（GPT-5.4-nano）在数学任务上比大模型（GPT-5.5）用标准方法还强25.4分；在电子表格任务上，小模型准确率0.7758，超过大模型的0.7620。更关键的是，这套流程只需开发者写一行“氛围代码”就能让智能体自我进化。它不是你明天就能直接用的工具，但揭示了AI自我优化的一个反直觉方向：少即是多。
📄 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.