VisCritic uses visual comparison of pre- and post-action GUI screenshots via a Siamese vision transformer and Action-Aware Critic Head to provide process rewards, improving agent performance on benchmarks.
arXiv preprint arXiv:2504.16073 (2025)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
VisCritic: Visual State Comparison as Process Reward for GUI Agents
VisCritic uses visual comparison of pre- and post-action GUI screenshots via a Siamese vision transformer and Action-Aware Critic Head to provide process rewards, improving agent performance on benchmarks.