[人人能懂] 从“攒答案”到“补短板”的决策智慧

00:00:26 高手过招：如何从一堆答案里“攒”出唯一正解？00:04:59 AI为什么也会“脑补”？00:10:17 AI刷题的“偏科”陷阱：如何让学霸更有创造力？00:15:19 一个AI学会做数学题，给了我们什么启发？00:21:20 目标太多，如何走上“最短路径”？本期介绍的几篇论文：[LG] The Majority is not always right: RL training for solution aggregation  [FAIR at Meta & CMU]  https://arxiv.org/abs/2509.06870  ---[LG] From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers  [Mila - Quebec AI Institute]  https://arxiv.org/abs/2509.06938  ---[LG] Outcome-based Exploration for LLM Reasoning  [FAIR at Meta]  https://arxiv.org/abs/2509.06941  ---[LG] Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers  [ByteDance Seed]  https://arxiv.org/abs/2509.06493  ---[LG] Simple Optimizers for Convex Aligned Multi-Objective Optimization  [Meta AI & Technion]  https://arxiv.org/abs/2509.05811  在小宇宙查看该单集文稿