News

Meng Lu is a Ph.D. student in computer science whose work focuses on complex planning with large language models (LLMs) to address intricate, data-driven challenges in real-world applications. Earlier this month, he was in Miami, Florida, where he and his advisor Xuan Wang presented “TriageAgent: Towards Better Multi-Agents Collaborations for Large Language Model-Based Clinical Triage” in main proceedings at the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP).

Another collaborator on the paper is Dennis Ren, assistant professor, Pediatric Emergency Medicine, Children’s National Hospital in Washington, D.C. 

“From the start, Professor Wang introduced me to several cutting-edge directions on LLMs, giving me a foundational understanding of complex reasoning, planning, and multi-agent collaboration with these models,” said Lu. “Under her guidance, I had the opportunity to collaborate with Children’s National Hospital to tackle the challenging task of clinical triage for complex medical documentation. This work led to a meaningful impact, where our solution performed comparably to professional human baselines and this experience ignited my passion for this field, and I am convinced that this research direction is both promising and impactful in the era of large models.”

Currently, he is exploring how multiple LLMs can collaborate effectively in dynamically changing environments through carefully crafted frameworks. 

“This involves designing LLM collaboration strategies that allow the models to act as intelligent agents within a data-driven environment, where they can extract, analyze, and interpret structured information from raw data sources. By tailoring these frameworks to real-world scenarios,” Lu said. “I work to enable LLMs to dynamically adapt their roles, share information efficiently, and solve complex, multi-layered problems. My research ultimately aims to create solutions that leverage data to guide the models’ collaborative strategies, achieving high performance in zero-shot and few-shot learning setups without extensive fine-tuning.”

Having earned a bachelor’s degree in electrical engineering from Hefei University of Technology, China, and a master’s degree in computer science from Northwestern University, Lu was attracted to Virginia Tech and the Sanghani Center by the professors’ expertise and many opportunities for quality collaborations to apply cutting-edge AI technology to real-world challenges.

In addition to Children’s National Hospital, Lu has had the opportunity to work with Amazon. These experiences haveallowed him to see – first-hand — how research can make a real difference. The guidance he received from experts, combined with access to high-quality research resources, has been invaluable in pushing the boundaries of his work with large language models, said Lu.

Projected to graduate in 2028, Lu hopes to join a research division of a major tech company in the United States. “I ameager to apply academic research to solve real-world problems and continue exploring the possibilities in AI,” he said.