SciReC：多模态多轮关系推理的自适应诊断评估
原标题：SciReC: Diagnostic Evaluation of Multimodal, Multi-Turn Relational Reasoning with Adaptive Interaction
AI 摘要
arXiv 论文提出 SciReC，一个模型自适应的多模态学术对话基准，用于评估多模态大语言模型在八类关系推理上的表现，并引入 DMRA 诊断框架以量化视觉理解、知识、记忆和推理等成分的贡献。结果显示 Claude 4.6 总体关系得分最高（73%），GPT 5.4 次之（68%）；开源模型在空间关系上最弱，闭源模型在层级和顺序关系上更吃力；所有模型的主要错误来源是关系推理本身，其次是记忆限制。
正文节选
SciReC: Diagnostic Evaluation of Multimodal, Multi-Turn Relational Reasoning with Adaptive Interaction Abstract Relational reasoning requires the process of perceptual understanding, comparing, and integrating the underlying relationships between concepts. This ability consists of multiple categories, such as analogical, structural, and cause-effect, each capturing a different aspect of higher-order understanding. To examine the performance of multimodal large language models (MLLM) on these rel