๐ MASCOT accepted to EMNLP 2026 Main as an oral presentation
Aug 20, 2026ยท
ยท
1 min read
Yiyang "Diana" Wang
MASCOT, our framework for multi-perspective socio-collaborative companions, was accepted to the EMNLP 2026 Main Conference as an oral presentation. MASCOT uses bi-level optimization to keep agents in character and make multi-agent dialogue more complementary and less sycophantic. Check out the paper, project page, and code.