StepGuard framework with DDPO and CANR claims SOTA navigation and answer accuracy on web benchmarks by switching policies and triggering reflection on low-confidence steps.
ScreenQA: Large-Scale Question-Answer Pairs Over Mobile App Screenshots , booktitle =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
StepGuard: Guarding Web Navigation via Single-Step Calibration
StepGuard framework with DDPO and CANR claims SOTA navigation and answer accuracy on web benchmarks by switching policies and triggering reflection on low-confidence steps.