Lingming Zhang (UIUC)
Title: Software Development in the Era of Large Language Models
Abstract
In recent years, Large Language Models (LLMs), such as GPT-4 and Claude-3.5, have shown impressive performance in various downstream applications. In this talk, I will discuss the impact of modern LLMs on critical software development problems, including software testing and program repair. In addition, I will also talk about the recent trend on leveraging LLMs to fully automate end-to-end software development tasks (i.e., AI software engineers), as well as our own Agentless work, which has been used by OpenAI to showcase the real-world coding performance of its recent models.
Bio
Lingming Zhang is an Associate Professor in the Department of Computer Science at the University of Illinois Urbana-Champaign. His main research interests lie in Software Engineering and Programming Languages, as well as their synergy with Machine Learning. His group has built a number of pioneering techniques on LLM-based software testing, repair, and synthesis (including TitanFuzz, AlphaRepair, and ChatRepair), with wide adoption in industry. In addition, his group has also released a series of competitive open-source code LLMs (including StarCoder2 and Magicoder), with over 1M downloads worldwide. He is a recipient of ACM SIGSOFT Early Career Researcher Award, NSF CAREER Award, UIUC Dean's Award for Excellence in Research, as well as research awards from Alibaba, Google, Kwai Inc., Meta, and Samsung. He currently serves as program co-chair for ASE 2025 and LLM4Code 2025, as well as associate chair for OOPSLA 2024. For more details, please visit: http://lingming.cs.illinois.edu/