This program supports AI startups at any time of the year. Benefit from cutting-edge resources and tailored support to accelerate your technology's development.
Offered by Mila and the Public Policy Forum, this program is designed to equip policy and decision makers with the tools to navigate the opportunities and risks of AI. The next cohort will be held in French on September 1-2, 2026, at Mila.
Connect with a Mila academic advisor and current student-researchers to learn more about Mila's community and how to join us on August 19, 31 and September 11, 2026.
We use cookies to analyze the browsing and usage of our website and to personalize your experience. You can disable these technologies at any time, but this may limit certain functionalities of the site. Read our Privacy Policy for more information.
Setting cookies
You can enable and disable the types of cookies you wish to accept. However certain choices you make could affect the services offered on our sites (e.g. suggestions, personalised ads, etc.).
Essential cookies
These cookies are necessary for the operation of the site and cannot be deactivated. (Still active)
Analytics cookies
Do you accept the use of cookies to measure the audience of our sites?
Multimedia Player
Do you accept the use of cookies to display and allow you to watch the video content hosted by our partners (YouTube, etc.)?
Zhiyuan Sun
Alumni
Publications
Enhancing Agent Learning through World Dynamics Modeling
Large language models (LLMs) have been increasingly applied to tasks in language understanding and interactive decision-making, with their i… (see more)mpressive performance largely attributed to the extensive domain knowledge embedded within them. However, the depth and breadth of this knowledge can vary across domains. Many existing approaches assume that LLMs possess a comprehensive understanding of their environment, often overlooking potential gaps in their grasp of actual world dynamics. To address this, we introduce Discover, Verify, and Evolve (DiVE), a framework that discovers world dynamics from a small number of demonstrations, verifies the accuracy of these dynamics, and evolves new, advanced dynamics tailored to the current situation. Through extensive evaluations, we assess the impact of each component on performance and compare the dynamics generated by DiVE to human-annotated dynamics. Our results show that LLMs guided by DiVE make more informed decisions, achieving rewards comparable to human players in the Crafter environment and surpassing methods that require prior task-specific training in the MiniHack environment.