Microsoft Research· Research / Phi

SkillOpt: Agent skills as trainable parameters

AI agents often fail because their instructions, or skills, are manually modified with no guarantee of improvement. SkillOpt turns skill editing into a training process, making agent behavior more reliable without changing model weights. SkillOpt treats an agent skill file as a trainable parameter outside a frozen target model, turning skill writing from one-shot prompting into a controlled optimization process. Across six benchmarks, seven target models, and three execution modes, SkillOpt is the best or tied-best method in all 52 evaluation cells, improving performance without updating model weights. SkillOpt keeps skills compact and auditable through bounded text edits, validation gating, rejected-edit feedback, and slow/meta updates, avoiding uncontrolled prompt drift. The optimized skills transfer across model scales, agent harnesses, and related tasks, suggesting that they capture reusable workflow knowledge rather than benchmark-specific instructions. Large language models (LLMs) are increasingly deployed as agents that gather evidence, call tools, and execute multi-step tasks. …

Announced

30 Jun 2026 16:50 UTC