ProgRM, a per-step progress reward model trained with LCS-based self-annotated labels, improves RL-trained GUI agent success rates on WikiHow relative to outcome reward models.
Digi-q: Learning vlm q-value functions for training device-control agents
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
ProgRM: Build Better GUI Agents with Progress Rewards
ProgRM, a per-step progress reward model trained with LCS-based self-annotated labels, improves RL-trained GUI agent success rates on WikiHow relative to outcome reward models.