SOURCE-LINKED INTELLIGENCE

COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Large language model (LLM) agents can benefit from reusable skills distilled from prior task experience, yet existing skill optimization methods often rely on costly execution-based evaluation and substantial task data. We introduce \textbf{COBRA-Skills}, an efficient framework that formulates skill optimization as budgeted sequential optimization over a dynamically evolving candidate space. COBRA-Skills couples contextual-bandit-guided prioritization with evidence-grounded skill evolution, selectively allocating evaluations to promising or informative candidates while continually refining the

Read original source ↗ Open in workspace

recordType

paper

region

Global