Skill-Learning on MLLog.devhttps://mllog.dev/en/tags/skill-learning/Recent content in Skill-Learning on MLLog.devMLLog.devhttps://mllog.dev/images/default_mllog.pnghttps://mllog.dev/images/default_mllog.pngHugo -- 0.147.9enFri, 29 May 2026 08:00:00 +0100SkillOpt: Training Agent Skills Like Neural Network Weights - Without Touching the Modelhttps://mllog.dev/en/posts/skillopt-text-space-optimizer-agent-skills/Fri, 29 May 2026 08:00:00 +0100https://mllog.dev/en/posts/skillopt-text-space-optimizer-agent-skills/SkillOpt applies deep-learning-style optimization - bounded edit budgets, validation gating, rejected-edit memory - to natural-language skill documents, improving frozen LLMs by up to +39 points across 52/52 evaluated cells without changing a single model weight.