SkillOpt-Lite:通过一行代码实现更好更快的智能体自我进化
SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe
AI总结:
研究智能体技能优化,通过零阶优化形式化,基于相关理念和学习建立收敛与泛化原则,提出SkillOpt-Lite加速收敛且性能优,还集成到生产编码智能体,最小管道可推广到完整 harness 优化。
摘要:
虽然自主智能体的技能优化受到关注,但现有方法依赖复杂管道。本文通过零阶优化形式化技能优化,基于相关理念和学习建立收敛与泛化三原则,提出SkillOpt-Lite,加速收敛且性能优,还集成到生产编码智能体,最小管道可推广到完整harness优化。代码可获取。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。