Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agents 事件

Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agents arXiv:2605.27955v1 Announce Type: cross Abstract: Markdown skill libraries for LLM agents ship as free-form prose, forcing the agent to re-derive both the input schema and the concrete invocation syntax on every retrieval. We observe that this often produces a "confused -> re-retrieve -> still confused" loop in which the agent issues a partially-correct action, receives uninformative environment feedback, and re-retri