Web World Models

Published in arXiv preprint, 2025

Prototyped a Web World Model framework that generates unlimited context via LLMs in text/code environments without data storage. Built multiple WWM-style environments spanning real-world and fictional settings (e.g., infinite world travel, infinite galaxy exploration), demonstrating controllable and open-ended interaction for users and agents.

Collaboration with Princeton AI Lab, Prof. Mengdi Wang.

Recommended citation: Web World Models. arXiv:2512.23676, 2025.
Download Paper