0:000:00
<p>本期的 5 篇论文如下：</p><p>[00:38] TOP1(🔥135) | 🌍 Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds（Lumine：在3D开放世界中打造通才智能体的开源方案）</p><p>[02:47] TOP2(🔥97) | 🖥 Grounding Computer Use Agents on Human Demonstrations（基于人类演示的计算机使用智能体定位研究）</p><p>[04:44] TOP3(🔥89) | 🧠 Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B（小模型大逻辑：多样性驱动优化唤醒VibeThinker-1.5B的大模型推理力）</p><p>[06:33] TOP4(🔥84) | 🧠 HaluMem: Evaluating Hallucinations in Memory Systems of Agents（HaluMem：智能体记忆系统幻觉评估基准）</p><p>[08:56] TOP5(🔥67) | 🧩 IterResearch: Rethinking Long-Horizon Agents via Markovian State Reconstruction（IterResearch：基于马尔可夫状态重构的长程智能体再思考）</p><figure><img src="https://image.xyzcdn.net/Fodt1QELn6exLkz4nzCwOyUV8MPL.webp"/></figure><p>【关注我们】</p><p>您还可以在以下平台找到我们，获得播客内容以外更多信息</p><p>小红书: AI速递</p>