Cheng Xue

Papers

Total Citations

H-Index

About

Cheng Xue is a researcher whose work sits at the intersection of artificial intelligence and cognitive science, with a primary focus on physical reasoning—the ability to understand and predict the behavior of objects in the physical world. Their major contribution is the development of **Phy-Q**, a novel benchmark and testbed designed to measure physical reasoning intelligence in AI agents. This work, detailed in their 2023 paper (9 citations) and a 2021 precursor (2 citations), addresses a critical gap: while humans intuitively reason about physics to accomplish tasks, this remains a profound challenge for AI. By creating a standardized framework to evaluate an agent’s capacity to navigate physical scenarios, Xue provides a vital tool for the AI research community. The Phy-Q benchmark not only highlights the limitations of current models but also sets a clear target for future progress, making it a foundational resource for anyone studying embodied intelligence, robotics, or cognitive architectures. Xue’s work is notable for bridging psychological concepts of intelligence with rigorous computational testing, offering a compelling path toward more human-like AI.