Zun Wang

LLM test generation quality is overestimated by 30% when evaluated against single references, with a new metric revealing widespread missed behaviors and faulty assertions.

FACET achieves unprecedented task synthesis quality by preserving source intent and ensuring executable state consistency, leading to more reliable terminal agents.

Agents trained in this framework achieve unprecedented improvements in reasoning depth and citation accuracy, transforming the landscape of automated peer review processes.

Decomposing GUI agent trajectories into verifiable milestones and auditing the evidence chain yields a 10% boost in RL training performance, outperforming single-judge reward systems.