Graphical User Interface (GUI) grounding is essential for autonomous agents to map natural language instructions to precise screen coordinates. However, existing supervised fine-tuning and reinforcement learning methods are constrained by the high cost of annotation, creating a scalability bottleneck. In this paper, we...
Yi-Zhou Liu, Fei Tang, Yuchen Yan et al.· 0 citations
Online training enables computer-use agents (CUAs) to improve through interaction with executable environments. However, existing methods primarily rely on sparse outcome rewards, which provide no supervision for intermediate actions. On-policy self-distillation (OPSD) offers token-level learning signals through privil...
Yong Du, Tong-I Chen, Zhengxi Lu et al.· 0 citations
This work derives second-moment stochastic approximation methods through the lens of optimal preconditioning for solving matrix equations, and develops a two-stage framework for their convergence analysis.
This is the first single-loop method for general nonexpansive fixed-point problems to attain this near-optimal sample complexity without variance reduction or batching.
Tong Yang, Tao Jiang, Yue-Jie Chi et al.· 0 citations
A dense process supervision method based on fact utility estimation, which models the reasoning process as the accumulation of discrete evidence facts, and converts the estimated fact utilities into dense step-level rewards to guide RL training.
Rongzhi Zhu, Xiang-Yu Liu, Yi Liu et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
