Pith. sign in

Digirl: Training in-the-wild device-control agents with autonomous re- inforcement learning

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.AI 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

ProgRM: Build Better GUI Agents with Progress Rewards

cs.AI · 2025-05-23 · conditional · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • ProgRM: Build Better GUI Agents with Progress Rewards cs.AI · 2025-05-23 · conditional · none · ref 2

    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.