Research
RELIC: building long-horizon agent organizations
A long-horizon testbed for LLM-agent organizations, including OrgEnv and professional profile graphs.
Read updateUPDATES / 2025—2026
From my research.
Updates on my papers, collaborations, and the questions I’m working through.
Collaboration
Joining the UIUC ATLAS Moonshot
Working on graph-grounded learning and reskilling, learner state, and human verification.
Read updatePublication
ProtocolBench accepted to ICML 2026
Our work studies multi-agent communication protocols and scenario-aware selection with ProtocolRouter. First-author paper.
Read updateCollaboration
Research collaboration with Northwestern
A remote collaboration with Manling Li’s lab, mentored by Qineng Wang, on 3D affordance research.
Read updatePublication
MultiAgentBench and EscapeBench at ACL 2025
Two co-authored papers accepted to the ACL main conference, studying interaction, collaboration, and agent problem solving.
Read update
Loading comments…