LLM Agents

The Geometry of Agent Skills: Non-Commutative Composition in Representation Space
A study of the geometry of agent skills and how their composition depends on order in representation space.
OpenReview
Skill-R1: Agent Skill Evolution via Reinforcement Learning
Skill-R1 trains a small generator to improve reusable natural-language procedures while keeping the task model fixed. Feedback from successive rollouts guides skill revisions, enabling adaptation with both open and closed models.
PDF