用注意力机制优化强化学习奖励，成功攻破大型推理模型的安全防线，揭示AI安全新挑战。
arXiv:2605.19485v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in solving complex problems by…
揭示推理预算为何无法调节人类与大型模型的认知成本对齐，努力是天花板而非旋钮。
arXiv:2605.16938v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) generate chain-of-thought traces whose length tracks human reaction time…
一篇关于通过KV缓存共享加速大型推理模型服务的系统优化论文，解决推理内存瓶颈问题。
arXiv:2507.21433v3 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) are becoming integral to many AI inference systems, enhancing …
PolitNuggets基准测试评估大模型在多语言长尾政治事实发现中的能力，为智能体信息合成提供新标尺。
arXiv:2605.14002v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) embedded in agentic frameworks have transformed information retrieval fr…