大模型空间推理常“答非所证”，这项研究用符号不确定性量化给结论可靠性加把锁，值得关注。
arXiv:2608.00417v1 Announce Type: new Abstract: Although large language models (LLMs) can produce fluent spatial reasoning traces, their intermediate …
首个系统评估LLM规划中潜在失败模式的基准，用世界模型揭示隐藏缺陷
arXiv:2606.14574v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as planners for autonomous agents in househol…
大模型面对误导医疗信息能否保持认知韧性？这项研究提供了系统测量方法
arXiv:2606.12291v1 Announce Type: new Abstract: Large language models (LLMs) now reach expert-level scores on medical licensing exams, encouraging the…
大型语言模型在数学推理中进步巨大，但可靠性问题如何解决？这篇论文用130道IMO竞赛题验证了AI驱动形式化证明搜索的潜力。
arXiv:2605.22763v1 Announce Type: new Abstract: Large language models (LLMs) increasingly excel at mathematical reasoning, but their unreliability lim…