本期的 5 篇论文如下:
[00:35] TOP1(🔥139) | 🤖 The Landscape of Agentic Reinforcement Learning for LLMs: A Survey(面向大语言模型的智能体强化学习全景:一项综述)
[01:52] TOP2(🔥133) | 🔒 A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code(A.S.E:一个用于评估AI生成代码安全的仓库级基准)
[02:57] TOP3(🔥127) | 🤖 A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers(科学大型语言模型综述:从数据基础到智能体前沿)
[04:15] TOP4(🔥103) | 🧠 R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning(R-4B: 通过双模式退火和强化学习激励多模态大语言模型的通用自动思考能力)
[05:11] TOP5(🔥101) | 🤔 Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth(废话学:用深度解读无意义内容挑战大型语言模型)
【关注我们】
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
小红书: AI速递
Information
- Show
- FrequencyUpdated Daily
- PublishedSeptember 6, 2025 at 11:00 PM UTC
- Length7 min
- RatingClean