StainFlow: Entity-Stain Tracking and Evidence Linking for Process Rewards in GUI Agents 事件

StainFlow: Entity-Stain Tracking and Evidence Linking for Process Rewards in GUI Agents arXiv:2606.07027v1 Announce Type: new Abstract: Reinforcement Learning (RL) has become a promising approach for improving GUI Agents in long-horizon, stochastic digital environments, but trajectory-level success feedback is too sparse to provide reliable credit assignment for intermediate exploration steps. To mitigate this issue, recent studies introduce Process Reward Models (PRMs), which provide finer-gra