Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM Agents

arXiv:2604.05013v1 Announce Type: cross Abstract: Current LLM coding agents are predominantly trained on composite benchmarks (e.g., bug fixing), which often leads to

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

arXiv:2608.12851v1 Announce Type: new Abstract: Self-improving LLM agents convert successful trajectories into persistent cross-task state. An unsafe success can thereby become

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

arXiv:2608.01050v1 Announce Type: new Abstract: Production LLM agents that select from large skill libraries face a limitation that semantic relevance alone cannot resolve: a

arXiv:2605.08693v1 Announce Type: new Abstract: Skills provide an effective mechanism for improving LLM agents on complex tasks, yet in existing agent frameworks, their creation,

arXiv:2604.04990v1 Announce Type: cross Abstract: AI coding agents select frameworks, scaffold infrastructure, and wire integrations, often in seconds. These are architectural