PILOT Seminar: Chunqiu Steven Xia, "Transforming Software Development in the Era of LLMs"
- Sponsor
- Siebel School of Computing and Data Science
- Originating Calendar
- Siebel School PILOT Seminars
Refreshments provided.
Abstract:
AI and large language models (LLMs) are opening a new era in how software is built, tested, and maintained. In this talk, I will discuss how to combine modern powerful LLM capabilities with traditional software engineering insights to 1) automate challenging and cognitively demanding software tasks, 2) enhance the reliability and trustworthiness of critical software systems, and 3) push the boundaries of AI coding and general reasoning. I will present my work advancing program repair, testing, and recent software agents demonstrating strong results on practical benchmarks as well as real-world industry impact and adoption. Together, these efforts highlight a promising path toward more capable, reliable, and impactful AI-driven software development.Bio:
Chunqiu Steven Xia is a PhD candidate in Computer Science at UIUC, advised by Professor Lingming Zhang. His research lies at the intersection of Software Engineering and Artificial Intelligence, with a focus on automating critical and cognitively demanding software development tasks using large language models (LLMs) and software agents. His work has significantly advanced how fundamental software problems are addressed in both academia and industry, uncovering 200+ critical bugs and vulnerabilities in widely used systems, and being adopted by leading AI companies, including OpenAI, Meta, DeepSeek, and MiniMax. His research has been recognized with an ACM SIGSOFT Distinguished Paper Award (FSE 2025), an Oral Spotlight Paper Award (COLM 2024), a CACM Research Highlight (FSE 2023), and the prestigious Amazon AICE PhD Fellowship.