SOURCE-LINKED INTELLIGENCE

Fractal basins trap latent reasoning

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

Reasoning allows artificial intelligence models to revisit and correct their mistakes, enabling recent frontier advances in mathematical theorem solving, software engineering, and autonomous task planning. Reasoning models are widely observed to reason for longer on harder tasks, but the general mechanism responsible for these slowdowns is unknown. Here, we show that reasoning models exhibit transient chaos, a physical consequence of the computational complexity of difficult tasks. As a consequence, we show that diverse leading reasoning models are dynamical systems with fractal basins, with f

Read original source ↗ Open in workspace

recordType

paper

region

Global