AI RESEARCH
Skill Availability and Presentation Granularity in Large-Language-Model Agents: A Controlled SkillsBench Study
arXiv CS.AI
•
ArXi:2605.31408v1 Announce Type: cross Skill documents provide procedural knowledge to large-language-model agents at inference time. This article studies whether the presentation granularity of controlled skill knowledge changes downstream task success. The experiment uses a pinned SkillsBench version, a 30-task domain-balanced subset validated by official oracle runs, two reasoning-enabled model configurations, six skill conditions, and five trials per task-condition-model cell. Skill availability is the clearest empirical signal.