Vision-Language Agents Can Learn in Their Own Latent Worlds
Learning from experience is essential for building the next generation of agents that continually expand their capabilities. Pretrained vision-language models (VLMs) already internalize rich world knowledge, yet this knowledge is rarely leveraged to drive policy improvement through online interaction. Realizing this potential efficiently remains challenging, as policy updates shift the agent's interaction distribution, requiring the world model to adapt accordingly, while continually updating large pretrained models is computationally expensive. To address this challenge, we introduce Dwell, a model-based reinforcement learning (RL) framework that reframes a VLM as a recurrent latent tran...
| Authors | Haoxi Li, Sikai Bai, Jianfei Ma et al. |
|---|---|
| Primary category | cs.AI |
| Published | 27 October 2026 |
| Last updated at source | 27 October 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 28 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.