29 papers
MECoBench: A Systematic Study of Multimodal Agent Collaboration in Embodied Environments
Qingyun Liu, Jiwen Zhang, Jingyi Hu +2
Recent multimodal large language models (MLLMs) have strong potential as embodied agents, but their ability to collaborate in visually grounded environments remains underexplored.…
Uncovering Salience-Driven Dynamics in Consumer Confidence with Generative Social Simulation
Yixu Huang, Yunlu Yin, Jiayu Lin +6
Consumer confidence is typically modeled as a persistent macroeconomic index, yet its movements arise from households that interpret economic information through heterogeneous cons…
LIBERO-Occ: Evaluating and Improving Vision-Language-Action Models under Scene-Induced Occlusion via Viewpoint Imagination
Taishan Li, Jiwen Zhang, Siyuan Wang +2
Vision-Language-Action (VLA) models achieve strong performance on standard manipulation benchmarks, but most evaluations assume that task-relevant objects are fully visible. This a…
Can Agents Read the Room? Benchmarking Visual Social Intelligence in Multimodal Simulation
Shijun Wan, Xuehai Wu, Jiwen Zhang +2
Social interaction depends on both language and visible social signals, such as facial expressions, posture, gaze, and emotional shifts. Yet existing social-agent benchmarks are la…
HyLaT: Efficient Multi-Agent Communication via Hybrid Latent-Text Protocol
Xinyi Mou, Siyuan Wang, Zejun Li +2
Communication protocol design is a central challenge in large language model-based multi-agent systems. Existing single-channel approaches face an inherent communication trilemma:…
Mixture-of-Visual-Thoughts: Exploring Context-Adaptive Reasoning Mode Selection for General Visual Reasoning
Zejun Li, Yingxiu Zhao, Jiwen Zhang +6
Current visual reasoning methods mainly focus on exploring specific reasoning modes. Although improvements can be achieved in particular domains, they struggle to develop general r…