Hybrid Advantage Estimation with Unified Critic for VLM Agentic Reinforcement Learning
Large Vision-Language Models (VLMs) now act as agents in interactive environments, where success requires coherent reasoning and decision-making across turns. Although end-to-end training in agentic environments can improve such multi-turn decision-making abilities, current methods mainly rely on either token-wise optimization over concatenated token trajectories or turn-wise optimization with uniform within-turn credit. In this work, we establish theoretical formulations for the two levels of optimization and derive a hybrid advantage that serves both objectives. Furthermore, with an appropriate choice of discount factor and learning target, we prove that a unified critic model can estim...
| Authors | Wenxuan Zhang, Yuhui Wang, Donggang Jia et al. |
|---|---|
| Primary category | cs.AI |
| Published | 26 July 2026 |
| Last updated at source | 26 July 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.