No AI summary available for this article.
Why It Matters
Recent web agents use world models for test-time action selection by sampling candidate actions, predicting the resulting web states, and ranking them with a ranker model or a Process Reward Model (PRM).
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Recent web agents use world models for test-time action selection by sampling candidate actions, predicting the resulting web states, and ranking them with a ranker model or a Process Reward Model (PRM). These world models are typically trained via supervised next-state prediction to generate fixed representations like HTML or AXTree snapshots. However, this objective is misaligned with the downstream ranker, which relies on predicted states being discriminative across candidates to accurately score them. To address this, we introduce predicted-state matching, a training objective where the pr...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.02885v1 · Indexed about 2 hours ago