AI RESEARCH
MASCOT: Towards Multi-Agent Socio-Collaborative Companion Systems
arXiv CS.AI
•
ArXi:2601.14230v2 Announce Type: replace-cross Multi-agent systems (MAS) are emerging as promising socio-collaborative companions for emotional and cognitive. However, existing systems frequently suffer from persona collapse, where agents revert to generic, homogenized assistant behaviors, and social sycophancy, where agents produce redundant, non-constructive dialogue. We propose MASCOT, a multi-agent framework for multi-perspective socio-collaborative companions.