Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Renmin University of China
3
0
7
5
Outcome-only RL can train highly effective process supervision models by rewarding accurate outcome prediction, even without explicit step-level feedback.
Multi-iteration experience learning in LLMs can lead to capability collapse, but strategic adjustments in experience granularity and injection patterns can stabilize and enhance performance.
Tool-using agents may seem capable, but they struggle to distinguish neutral actions from errors, highlighting a critical need for better step-level process understanding.