AI RESEARCH

When Skills Don't Help: A Negative Result on Procedural Knowledge for Tool-Grounded Agents in Offensive Cybersecurity

arXiv CS.AI

ArXi:2605.20023v1 Announce Type: new Agent Skills, structured packages of procedural knowledge loaded into an LLM agent at inference time, are widely reported to improve task pass rates by an average of 16.2~percentage points across diverse domains. Yet the same benchmarks show wide variance, with 16 of 84 tasks suffering negative deltas when Skills are