AI RESEARCH
GraSP: Graph-Structured Skill Compositions for LLM Agents
arXiv CS.CL
•
ArXi:2604.17870v1 Announce Type: new Skill ecosystems for LLM agents have matured rapidly, yet recent benchmarks show that providing agents with skills does not monotonically improve performance -- focused sets of 2-3 skills outperform comprehensive documentation, and excessive skills actually hurt. The bottleneck has shifted from skill availability to skill orchestration: agents need not skills, but a structural mechanism to select, compose, and execute them with explicit causal dependencies. We propose GraSP, the first executable skill graph architecture that.