1
Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models
揭秘多模态大模型推理时感知下降现象及缓解策略，为AI可靠性提供关键洞察
arXiv:2603.14184v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) often suffer from perceptual impairments under extended r…