ProRe uses reasoner-actor collaboration for proactive state probing to assign accurate rewards to GUI agents, improving accuracy by 5.3% and policy success rates by 22.4% on over 3K trajectories.
- Mark as **contradicted** if an evaluator claim directly disproves a policy claim
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ProRe: A Proactive Reward System for GUI Agents via Reasoner-Actor Collaboration
ProRe uses reasoner-actor collaboration for proactive state probing to assign accurate rewards to GUI agents, improving accuracy by 5.3% and policy success rates by 22.4% on over 3K trajectories.