ASD: Automated Skill Discovery through Agent Directed Optimization

Large language model (LLM) systems are increasingly equipped with skills to improve task performance. Recent methods automate the development of these skills from execution feedback, but the optimization process itself typically follows human-designed rules. We investigate whether an agent can instead design and direct the skill discovery process. We introduce Automated Skill Discovery (ASD), a framework in which a discovery agent develops a skill library for a target model by autonomously designing and adapting the optimization procedure. In ASD, the target model selects and loads skills as needed for each problem, reducing the input context by approximately 69% compared with including all skills in the model's context. We evaluate ASD on eight open-weight models across five benchmarks spanning question answering, mathematics, and software engineering. ASD improves test success over the base model by 16.2 points on average and outperforms the human-designed optimization baselines on each benchmark. We further investigate ASD in a mixed-task setting, where a single library developed for each target model supports four tasks, improving test success over the base model by 14.3 points.