这篇论文用物理能量模型解释推理，让Phi-3.5在GSM8K上提了5.38%，思路挺新。
该论文提出一种受物理启发的推理机制，将大语言模型视为高维密集联想记忆体。作者通过吉布斯权重对多个推理路径进行加权（P∝e^{-βE}），使模型收敛到更稳定的吸引子盆地。实验表明，该方法在GSM8K上将微软Phi-3.5的准确率从84.7%提升至90.1%，提升5.38%。这揭示了推理过程更像动态松弛而非贪婪词预测。
Reasoning as Attractor Dynamics: Latent Memory Retrieval via Gibbs-Weighted Energy Minimization
Large Language Models (LLMs) are traditionally viewed as autoregressive generators. However, from the perspective of collective computation, they function as high-dimensional Dense Associative Memories that store complex reasoning patterns as latent attractors. In this work, we investigate the energy landscape of mathematical reasoning. We posit that correct reasoning chains correspond to deep, wide attractor basins ("flat minima") in the model's output distribution, whereas hallucinations manifest as sharp, unstable local minima. To exploit this geometry, we introduce a retrieval mechanism based on a Gibbs measure of the trajectory's spectral entropy. By sampling multiple reasoning paths and weighting them by their inverse energy ($P \propto e^{-βE}$), we approximate the equilibrium distribution of the associative memory, effectively ``relaxing'' the system into a robust solution. Empirically, this physics-inspired mechanism improves Microsoft Phi-3.5 performance on GSM8K by 5.38\% (84.7\% $\to$ 90.1\%), demonstrating that inference is better modeled as a dynamic settling process into an attractor basin rather than greedy next-token prediction.