1
Model Collapse as Cultural Evolution
从文化演化理论解释大模型自我训练导致的模型崩溃，提出五个可证伪预测，填补语言学空白。
arXiv:2605.23054v1 Announce Type: cross Abstract: Model collapse, the progressive degradation of LLMs trained on their own outputs, has been character…
2
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design
提出轨迹级评估框架LEAP，首次量化LLM在科学设计中的迭代学习过程，而非仅关注结果快照。
arXiv:2605.15341v1 Announce Type: cross Abstract: LLMs are increasingly deployed in autonomous laboratories, under the assumption that their domain pr…