Evaluating Multimodal Large Language Models with Daily Composite Tasks in Home Environments
This work addresses the challenge of assessing general capabilities for embodied agents in real-world settings, though it is incremental as it provides a preliminary evaluation framework.
The authors tackled the problem of evaluating whether multimodal large language models (MLLMs) can solve composite tasks in home environments, and found that 17 leading MLLMs performed poorly across object understanding, spatial intelligence, and social activity domains, indicating a substantial gap from general intelligence requirements.
A key feature differentiating artificial general intelligence (AGI) from traditional AI is that AGI can perform composite tasks that require a wide range of capabilities. Although embodied agents powered by multimodal large language models (MLLMs) offer rich perceptual and interactive capabilities, it remains largely unexplored whether they can solve composite tasks. In the current work, we designed a set of composite tasks inspired by common daily activities observed in early childhood development. Within a dynamic and simulated home environment, these tasks span three core domains: object understanding, spatial intelligence, and social activity. We evaluated 17 leading proprietary and open-source MLLMs on these tasks. The results consistently showed poor performance across all three domains, indicating a substantial gap between current capabilities and general intelligence requirements. Together, our tasks offer a preliminary framework for evaluating the general capabilities of embodied agents, marking an early but significant step toward the development of embodied MLLMs and their real-world deployment.