Group Meeting | 2025-12-01

Evaluating urban visual attractiveness perception using multimodal large language model and street view images

Reinforcement Learning Improves Traversal of Hierarchical Knowledge in LLMs

本文系统分析了语言模型的结构化导航能力，提出结构提示与路径匹配指标，揭示强化学习主要提升了模型对复杂查询的处理路径而非知识本体