为大模型应用场景选择提供诊断工具，探究语言驱动赌博机何时需要LLM。
arXiv:2604.05859v2 Announce Type: replace Abstract: We study Contextual Multi-Armed Bandits (CMABs) for non-episodic decision-making problems where th…
诊断大模型数据配比的“DNA”，ACL 2026主会论文开源代码
arXiv:2605.30348v1 Announce Type: cross Abstract: The pretraining data mixture of Large Language Models (LLMs) constitutes their "digital DNA", shapin…
聚焦长链思维训练中“答案正确但有害”的隐蔽问题，提出诊断方法助你避开模型训练陷阱。
arXiv:2605.29288v1 Announce Type: new Abstract: Long chain-of-thought (CoT) traces are widely used as supervision for reasoning-oriented LLM SFT, yet …
一种基于见证解析档案的新方法，用于实时诊断LLM代理在执行策略时的指令冲突问题。
arXiv:2605.27784v1 Announce Type: new Abstract: LLM agents are governed by long-lived natural-language prompt policies, but individually reasonable st…
视频大模型竟会“运动盲视”？研究揭示其方向识别缺陷并提出数据与模型改进方案。
arXiv:2605.22823v1 Announce Type: new Abstract: Video Large Language Models (Video-LLMs) have made rapid progress on temporal video understanding, yet…