VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning

Understand

Coordinating multiple embodied agents in dynamic environments remains a core challenge in artificial intelligence, requiring both perception-driven reasoning and scalable cooperation strategies.

• While recent works have leveraged large language models (LLMs) for multi-agent planning, a few have begun to explore vision-language models (VLMs) for visual reasoning.
• However, these VLM-based approaches remain limited in their support for diverse embodiment types.
• In this work, we introduce VIKI-Bench, the first hierarchical benchmark tailored for embodied multi-agent cooperation, featuring three structured levels: agent activation, task planning, and trajectory perception.