2 papers
cs.AI2026
UniOPSD: Unifying Outcome and Hindsight Feedback for Agentic Reinforcement Learning
Zenghuang Fu, Zhaoyang Li, Qiuyuan Ai +8
Reinforcement learning has become an effective approach to training language model agents, but sparse and delayed outcome rewards provide limited guidance for credit assignment acr…
cs.AI2026
SIPO: Selective-Inference Policy Optimization for Tree-Structured Agentic RL
Zenghuang Fu, Ningqi Chen, Mingda Jia +10
Tree-structured reinforcement learning trains search agents by comparing alternative continuations and propagating terminal rewards to intermediate decisions. Adaptive expansion, h…