Model Releases
COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization
arXiv:2609.11682v1 Announce Type: new Abstract: Large language model (LLM) agents can benefit from reusable skills distilled from prior task experience, yet existing skill optimization methods often r
arXiv:2609.11682v1 Announce Type: new Abstract: 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 extbf{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 skill population from execution feedback. Across six heterogeneous agent benchmarks and three target models, COBRA-Skills consistently achieves the strongest average performance among compared methods, while reducing optimization cost by 55--58% relative to SkillOpt and using only 50 unique optimization examples per benchmark. Further analyses show that COBRA-Skills remains robust to changes in the agent harness and performs effectively when the target model itself is used for skill generation and refinement.
Related
- SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories
- SkillCommit: Evolving Agent Skills through Behaviorally Validated Scope Expansion
- SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills
- SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe
Source: arXiv cs.AI | 2026-09-12