As artificial intelligence (AI) increasingly permeates our everyday existence, upcoming significant obstacles involve ensuring effective cooperation between AI systems and human operators, alongside nurturing confidence in this technology, assert computer scientists William Yeoh and Stylianos Vasileiou from the McKelvey School of Engineering at Washington University in St. Louis.

“Moving ahead, it’s crucial for individuals to have a suitable level of faith in what AI can accomplish for them,” Yeoh stated. “A method to attain that is to have the system clarify why it operates the way it does in an interactive and comprehensible manner.”

To tackle these issues, Yeoh, an associate professor of computer science and engineering, along with Vasileiou, a graduate researcher in Yeoh’s lab, devised TRACE-cs, an innovative hybrid tool that addresses the specific challenge of students’ course scheduling. The tool produces precise explanations efficiently in a quickly digestible format — a groundbreaking progression in the domain. Vasileiou showcased TRACE-cs on Feb. 28 at the 2025 AAAI Conference on Artificial Intelligence.

TRACE-cs merges symbolic reasoning with the natural language functionalities of large language models to deliver reliable, easily comprehensible support for intricate decision-making activities. TRACE-cs guarantees accuracy by integrating user validation and permitting follow-up inquiries, while enhancing usability by emphasizing succinctness in the explanations of suggested schedules.

Discover more on the McKelvey Engineering website.

The article AI tool assists in making trustworthy, explainable scheduling decisions was originally published on The Source.