UCOB: Learning to Utilize and Evolve Agentic Skills

SIGNAL ANALYSIS

Offline reinforcement learning agents fail in production because static training datasets cannot cover the full range of real-world scenarios. UCOB addresses this by learning to utilize and evolve agentic skills via credit-aware on-policy bidirectional self-distillation, effectively giving the agent an expanding behavioral library without online interaction. This unlocks RL for applications where collecting live experience is dangerous or expensive.