No AI summary available for this article.
Why It Matters
GUI agents automate tasks on digital devices by grounding language instructions in visual interfaces.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
GUI agents automate tasks on digital devices by grounding language instructions in visual interfaces. Existing group-relative reinforcement learning improves GUI action prediction by comparing the rewards of multiple responses sampled from the same GUI state. However, binary evaluation treats spatially different failed clicks as identical and provides no relative signal when all sampled clicks fail. To address these limitations, we propose Spatial Credit Assignment (SCA), which uses the screen coordinates of sampled clicks to refine group-relative credit. Specifically, SCA predicts each held-o...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.36939v1 · Indexed about 2 hours ago