MOSAIC: A Universal Agent-Level Interface for Cross-Paradigm Agent Mixing and Human-AI Collaboration
MOSAIC is an open-source platform that enables heterogeneous agents (RL policies, LLMs, VLMs, and human operators) to act within shared reinforcement learning environments in ad-hoc team settings with reproducible results.
Abdulhamid M. Mousa, Jin-Hui Pang, Rakhmonberdi Khajiev et al.
· 0 citations