This work was done during one weekend by research workshop participants and does not represent the work of Apart Research.
Accepted at the 
 research sprint on 
October 2, 2023

Exploring Failures: Assessing Large Language Model in General Sum Games with Imperfect Information Against Human Norms

In this report, we explore LLMs for general sum games with Imperfect Information. We consider three games,including Chameleon, One Night Ultimate Werewolf, and Avalon. These games were chosen due to their inherent characteristics of imperfect information and present an ascending order of complexity in terms of logical reasoning and information processing.

Ziyan Wang, Shilong Deng, Zijing Shi, Meng Fang, Yali Du
4th place
3rd place
2nd place
1st place
 by peer review