Research Arm
We study the intelligence we are to shape the intelligence we build.
AAAI Spring Symposium 2026ICLR HCAIR Workshop
MIRROR: Cognitive inner monologue for persistent reflection and reasoning in conversational LLMs.
A cognitive architecture that gives language models an inner monologue between turns, so they reflect, hold context, and resist sycophancy across a conversation.
ICLR LLA Workshop
YOAO: You Only Align Once — propagating cooperative behaviors in multi-agent systems.
Cooperative behavior spreads through a network of agents without retraining, scaling held-out cooperation from 26% to 96%.