你有没有想过，AI解决难题，是靠“刷题”蒙对答案，还是真的理解了过程？在本期节目中，我们将看到最新论文如何教会AI养成“打草稿”的思考习惯，又如何在没有标准答案时，学会倾听宝贵的“少数派声音”。让我们一起探索，AI如何从一个“会说话的机器”进化为一个真正的“思考者”。00:00:29 AI如何学会思考？一个奖励机制的悄然革命00:05:15 高手过招，如何不“钻牛角尖”？00:09:45 AI的集体智慧：当少数派报告比多数票更重要00:15:11 AI换个思路看世界：当化学家扔掉“说明书”之后00:21:15 好模型，不只看结果，更要看过程本期介绍的几篇论文：[LG] RLP: Reinforcement as a Pretraining Objective [NVIDIA & CMU] https://arxiv.org/abs/2510.01265 ---[LG] RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems [CMU & Stanford University] https://arxiv.org/abs/2510.02263 ---[CL] RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization [Iowa State University & Meta & UW–Madison] https://arxiv.org/abs/2510.02172 ---[LG] Transformers Discover Molecular Structure Without Graph Priors [UC Berkeley] https://arxiv.org/abs/2510.02259 ---[LG] Step-Aware Policy Optimization for Reasoning in Diffusion Large Language Models [CMU] https://arxiv.org/abs/2510.01544

Ask this episode

“What did the council decide on item 42?” — answered with the speaker and the moment.

Transcript

Related