一作ACL 2026Poster· Natural Language Processing
DIXITWORLD : Evaluating Multimodal Abductive Reasoning in Vision-Language Models with Multi-Agent Dixit Gameplay
Yunxiang MO · Tianshi Zheng · Qing Zong · Jiayu Liu · Baixuan Xu · Yauwai Yim · Chunkit Chan · Jiaxin Bai · Yangqiu Song
摘要
Multimodal abductive reasoning — the generation and selection of explanatory hypotheses from partial observations — is a cornerstone of intelligence. Current evaluations of such ability in vision–language models (VLMs) are largely confined to static, single-agent tasks. Inspired by Dixit, we intr...