1
Whatever the mirror test tells us, beluga whales pass it
白鲸通过镜子测试，但这项自我认知实验本身正受到科学界越来越大的质疑
The white whales join the short, contested list of animals that see themselves.
2
Reliability and Effectiveness of Autonomous AI Agents in Supply Chain Management
深入研究AI代理在供应链中的可靠性与有效性，揭示自主决策对物流效率的实际影响。
arXiv:2605.17036v1 Announce Type: cross Abstract: This paper studies autonomous generative AI agents in multi-echelon supply chains using the MIT Beer…
3
GhostCite: A Large-Scale Analysis of Citation Validity in the Age of Large Language Models
大规模实证分析揭示大语言模型时代引文造假现象，拷问学术信任根基
arXiv:2602.06718v2 Announce Type: replace-cross Abstract: Citations provide the basis for trusting scientific claims; when they are invalid or fabrica…
4
JSON-Bag: A generic game trajectory representation
用JSON-Bag模型将游戏轨迹转化为通用向量表示，通过JSD度量和原型近邻搜索高效评估轨迹相似性。
arXiv:2508.00712v2 Announce Type: replace Abstract: We introduce JSON Bag-of-Tokens model (JSON-Bag) as a method to generically represent game traject…