LongPuzzleBench: Evaluating GUI Agents on Long-Horizon Visual Puzzles
This work introduces LongPuzzleBench, 114 levels in six puzzle games played through native GUI actions, where one objective can take a human over a thousand actions on persistent boards and dead ends go unannounced.
Bing-Xu Zhang, Hao-Chuan Lu, Zong-Jie Li et al.
· 0 citations