作者位次 #4/6ACL 2026Poster· Natural Language Processing
When Seeing Is not Enough: Revealing the Limits of Active Reasoning in MLLM s
Hongcheng Liu · Pingjie Wang · Yuhao Wang · Siqu Ou · Yanfeng Wang · Yu Wang
摘要
Multimodal large language models (MLLMs) have shown strong capabilities across a broad range of benchmarks. However, most existing evaluations focus on passive inference, where models perform step-by-step reasoning under complete information. This setup is misaligned with real-world use, where se...