Frontier LRMs match human game-learning behavior and predict fMRI signals an order of magnitude better than RL or Bayesian agents because of their in-context game-state representations.
The state was computed as a frame difference (current_screen - last_screen) rather than using stacked frames or raw frames
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Reason to Play: Behavioral and Brain Alignment Between Frontier LRMs and Human Game Learners
Frontier LRMs match human game-learning behavior and predict fMRI signals an order of magnitude better than RL or Bayesian agents because of their in-context game-state representations.