Xingyao Wang

AI agents that ace isolated coding tasks fall apart when faced with the messy reality of continuous software evolution, dropping from 80% to 38% success rates in a new benchmark.

Learn a critic for coding agents from human-in-the-loop interaction traces alone, sidestepping the need for dense, verifiable rewards.

Forget one-size-fits-all models: personalized speech analysis can now predict heart failure deterioration with nearly perfect accuracy (99.7%).

Forget training on narrow GitHub issues – Hybrid-Gym unlocks surprisingly broad coding skills by teaching agents to explore codebases and design architectures in synthetic environments.