AI RESEARCH
MirrorBench: Evaluating Self-centric Intelligence in MLLMs by Introducing a Mirror
arXiv CS.AI
•
ArXi:2604.14785v1 Announce Type: new Recent progress in Multimodal Large Language Models (MLLMs) has nstrated remarkable advances in perception and reasoning, suggesting their potential for embodied intelligence. While recent studies have evaluated embodied MLLMs in interactive settings, current benchmarks mainly target capabilities to perceive, understand, and interact with external objects, lacking a systematic evaluation of self-centric intelligence. To address this, we