Kai Qiu

Simulating professional organizations with persistent context and delegation unlocks emergent agent capabilities, outperforming single- and multi-agent baselines on complex professional tasks.

Larger RLVR batches, despite appearing efficient with square-root learning rates, suffer a critical batch size that degrades sample efficiency and hastens failure due to curvature effects.

Aesthetic code generation is unlocked by using a VLM judge to translate visual design principles from a reference image into actionable rewards for code models.