发表机构
The Oden Institute, The University of Texas at Austin; The University of Texas at Austin; Department of Physics, The University of Texas at Austin（德克萨斯大学奥斯汀分校奥登研究所; 德克萨斯大学奥斯汀分校; 德克萨斯大学奥斯汀分校物理系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究发现推理模型存在随任务难度增加分形程度提升的分形盆地瞬态混沌，揭示推理减速是AI模型问题难度的必然结果，确立推理轨迹为新型动力系统。
AI 中文摘要
推理使人工智能模型能够回顾并修正自身错误，推动了其在数学定理证明、软件工程和自主任务规划等前沿领域的进展。人们普遍观察到，推理模型在更困难的任务上会进行更长时间的推理，但导致这种减速的通用机制尚不明确。本文表明，推理模型表现出瞬态混沌，这是困难任务计算复杂性的物理结果。因此，多种主流推理模型是具有分形盆地的动力系统，在数独、迷宫求解、视觉谜题和数学逻辑等不同任务中，分形程度随任务难度增加而提升。研究显示，瞬态混沌的出现是因为推理过程被长时间困在鞍点附近，而这些鞍点对应着基础问题的近似正确尝试解。研究结果表明，推理减速是现代人工智能模型中问题难度的必然结果，并确立推理轨迹为一类丰富的新型动力系统。
英文摘要
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 fractality increasing with task difficulty across diverse tasks like Sudoku and maze solving, visual puzzles, and mathematical logic. We show that transient chaos emerges due to reasoning becoming trapped for extended durations near saddle points, which we show correspond to nearly-correct attempted solutions of the underlying problem. Our results show that reasoning slowdowns are an inevitable consequence of problem hardness in modern artificial intelligence models, and establish reasoning traces as a rich new class of dynamical system.
Comments6 pages, 5 figures
