AI RESEARCH
IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents
arXiv CS.AI
•
ArXi:2604.05157v1 Announce Type: new Computer-Use Agents (CUAs) leverage large language models to execute GUI operations on desktop environments, yet they generate actions without evaluating action quality, leading to irreversible errors that cascade through subsequent steps. We propose IntentScore, a plan-aware reward model that learns to score candidate actions from 398K offline GUI interaction steps spanning three operating systems. IntentScore trains with two complementary objectives: contrastive alignment for state-action relevance and margin ranking for action correctness.