AI RESEARCH
SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration
arXiv CS.AI
•
ArXi:2605.14089v1 Announce Type: new In recent years, a variety of powerful LLM-based agentic systems have been applied to automate complex tasks through task orchestration. However, existing orchestration methods still face key challenges, including strategy collapse under reward maximization, high gradient variance with opaque credit assignment, and unguided skill evolution whose decisions are typically made by directly prompting an LLM to judge rather than derived from principled