难度感知熵正则化，让大模型推理时自动压缩简单问题算力，集中资源攻克难题，效率与精度兼得。
arXiv:2602.22642v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) has substantially empowered Large Language Models (LLMs) to tackle complex …
多智能体LLM协调稳定性新方案：熵正则化均衡选择，突破传统博弈论限制。
arXiv:2606.08068v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems often fail to reliably outperform a single strong model…
提出Policy Split方法，用双模式熵正则化激励LLM强化学习中的探索，平衡探索与利用。
arXiv:2604.11510v2 Announce Type: replace-cross Abstract: To encourage diverse exploration in reinforcement learning (RL) for large language models (L…
平均场朗之万动力学的镜像变体，为无穷宽神经网络训练提供新理论视角
arXiv:2505.02621v2 Announce Type: replace Abstract: The mean-field Langevin dynamics (MFLD) minimizes an entropy-regularized nonlinear convex function…