作者位次 #7/11ACL 2026Findings· Findings of ACL
A da T ooler- V : Adaptive Tool-Use for Images and Videos
Chaoyang Wang · Kaituo Feng · Dongyang Chen · Zhongyu Wang · Zhixun Li · Sicheng Gao · Meng Meng · Xu Zhou · Manyuan Zhang · Yuzhang Shang · Xiangyu Yue
摘要
Recent advances have shown that multimodal large language models (MLLMs) benefit from multimodal interleaved chain-of-thought (CoT) with vision tool interactions. However, existing open-source models often exhibit blind tool-use reasoning patterns, invoking vision tools even when they are unneces...