Yucheng Shi

Recursive task synthesis not only slashes generation costs to $0.05 per task but also produces increasingly complex challenges that boost model performance by up to 10 points on key benchmarks.

Staleness-Adaptive Trust Regions reshape update geometry in asynchronous reinforcement learning, achieving record performance while controlling for high-staleness updates.

Behavior localization is revolutionized, enabling developers to seamlessly connect high-level modification requests to specific code locations in complex AI harnesses.

Agents struggle with long-horizon tasks, achieving only a 15.2% success rate even with advanced models, highlighting a critical gap in current AI capabilities.

Achieving near-optimal accuracy while slashing costs, this cascaded framework ensures only the toughest queries hit the expensive models.

Combining soft correctness-aware gating with teacher-probability scaling leads to a substantial boost in GUI grounding performance, revealing the critical importance of signal quality in self-distillation.

Real-time skill adaptation for web agents boosts automation success rates by over 10% compared to static methods.