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 paper introduces Implicit Social Context Analysis (MoCA), a novel task that systematically models implicit social scenarios along three key dimensions: affection, intent, and stance, and proposes Conflict-Driven Abductive Reasoning (CoDAR), a novel framework that models the discrepancy between observed expressions...
Wen-Hao Xu, Kaiwen Zhang, Hao Li 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.
