Reinforcement Learning for Multimodal Foundation Models: A Survey
ACM Computing Surveys · 12.08.2026
DOI: 10.1145/3837760 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 12.08.2026. Verfasst von Weijia Wu und 8 weiteren Autor:innen. Die Arbeit nennt 245 Literaturangaben.
Abstract (Originalsprache)
Recent advances at the intersection of reinforcement learning (RL) and Multimodal Foundation Models have enabled agents that not only perceive complex visual scenes but also reason, generate, and act within them. This survey offers a critical and up-to-date synthesis of the field. We first formalize visual RL problems and trace the evolution of policy-optimization strategies from RLHF to verifiable reward paradigms, and from Proximal Policy Optimization to Group Relative Policy Optimization. We then organize more than 200 representative works into four thematic pillars: multi-modal large language models, visual generation, unified model frameworks, and vision-language-action models. For each pillar we examine algorithmic design, reward engineering, benchmark progress, and we distill trends such as curriculum-driven training, preference-aligned diffusion, and unified reward modeling. Finally, we review evaluation protocols spanning policy-level, trajectory-level preference, and training diagnostic stability, and we identify open challenges that include sample efficiency, generalization, and safe deployment. Our goal is to provide researchers and practitioners with a coherent map of the rapidly expanding landscape of visual RL and to highlight promising directions for future inquiry. Resources are available at: https://github.com/weijiawu/Awesome-RL-for-Multimodal-Foundation-Models.
Zitieren
APA
Wu, W., Gao, C., Chen, J., Lin, Q., Meng, Q., Zhang, Y., Qiu, Y., Zhou, H., & Shou, Z. (2026). Reinforcement Learning for Multimodal Foundation Models: A Survey. ACM Computing Surveys. https://doi.org/10.1145/3837760
Vancouver
Wu W, Gao C, Chen J, Lin Q, Meng Q, Zhang Y, et al. Reinforcement Learning for Multimodal Foundation Models: A Survey. ACM Computing Surveys. 2026. doi:10.1145/3837760
BibTeX
@article{Wu2026,
author = {Wu, Weijia and Gao, Chen and Chen, Joya and Lin, Qinghong and Meng, Qingwei and Zhang, Yiming and Qiu, Yuke and Zhou, Hong and Shou, Zheng},
title = {Reinforcement Learning for Multimodal Foundation Models: A Survey},
journal = {ACM Computing Surveys},
year = {2026},
doi = {10.1145/3837760}
}
EUVIMED