SkillOpt: Agent skills as trainable parameters

<p>After building 50+ AI systems, here is what we know about optimizing AI agent skills.</p> <p>SkillOpt is a groundbreaking open-source framework developed by Microsoft that

arXiv:2609.25299v1 Announce Type: new Abstract: On repeated work, agents are inconsistent. We ran 42 tasks three times each and found that, depending on the model, 38% to 74%

arXiv:2604.05333v1 Announce Type: new Abstract: Skill usage has become a core component of modern agent systems and can substantially improve agents' ability to complete complex

arXiv:2605.06702v1 Announce Type: new Abstract: Large language models (LLMs) have become a central foundation of modern artificial intelligence, yet their lifecycle remains

arXiv:2605.15215v1 Announce Type: new Abstract: Recently, skills have been widely adopted in large language model (LLM)-based agent systems across various domains. In existing

arXiv:2604.15877v1 Announce Type: new Abstract: As LLM agents scale to long-horizon, multi-session deployments, efficiently managing accumulated experience becomes a critical