[Paper] OS-Themis: A Scalable Critic Framework for Generalist GUI Rewards

Published: (March 19, 2026 at 01:47 PM EDT)
2 min read
Source: arXiv

Source: arXiv - 2603.19191v1

Overview

Reinforcement Learning (RL) has the potential to improve the robustness of GUI agents in stochastic environments, yet training is highly sensitive to the quality of the reward function. Existing reward approaches struggle to achieve both scalability and performance. To address this, we propose OS-Themis, a scalable and accurate multi-agent critic framework. Unlike a single judge, OS-Themis decomposes trajectories into verifiable milestones to isolate critical evidence for decision making and employs a review mechanism to strictly audit the evidence chain before making the final verdict. To facilitate evaluation, we further introduce OmniGUIRewardBench (OGRBench), a holistic cross-platform benchmark for GUI outcome rewards, where all evaluated models achieve their best performance under OS-Themis. Extensive experiments on AndroidWorld show that OS-Themis yields a 10.3% improvement when used to support online RL training, and a 6.9% gain when used for trajectory validation and filtering in the self-training loop, highlighting its potential to drive agent evolution.

Key Contributions

This paper presents research in the following areas:

  • cs.AI

Methodology

Please refer to the full paper for detailed methodology.

Practical Implications

This research contributes to the advancement of cs.AI.

Authors

  • Zehao Li
  • Zhenyu Wu
  • Yibo Zhao
  • Bowen Yang
  • Jingjing Xie
  • Zhaoyang Liu
  • Zhoumianze Liu
  • Kaiming Jin
  • Jianze Liang
  • Zonglin Li
  • Feng Wu
  • Bowen Zhou
  • Zun Wang
  • Zichen Ding

Paper Information

  • arXiv ID: 2603.19191v1
  • Categories: cs.AI
  • Published: March 19, 2026
  • PDF: Download PDF
0 views
Back to Blog

Related posts

Read more »