Abstract

This talk traces how AI-driven software engineering—particularly bug finding—has evolved over two decades: from statistical machine learning and handcrafted features to today’s large language models and agentic pipelines. The central bottleneck has shifted—from features to data, and from implementation to validation and verification. Drawing on work spanning automated code generation, bug and vulnerability detection and repair, binary analysis, and robot task planning, this talk argues that the field is undergoing a broader transition from features to data and domain knowledge. Here, “code” is interpreted broadly: beyond source code to binaries, HTML and CSS, and LaTeX—and beyond functional correctness to maintenance and security. LLMs are powerful across all of these settings, yet they are not a silver bullet: they hallucinate fixes, overfit to test suites, and degrade on real-world tasks. The talk closes by examining what will likely define the decade ahead for software engineering research, including data generation, specification- and test-driven software development, rigorous benchmarks, and neurosymbolic AI.

Speaker Bio

Lin Tan is a Professor and University Faculty Scholar in the Department of Computer Science at Purdue University and an Amazon Scholar. Previously, she was a Canada Research Chair and an associate professor at the University of Waterloo. Her research interests include software-AI synergy (AI4Software and Software4AI), LLM4Code, software dependability, autoformalization, and software text analytics. Dr. Tan is an IEEE Fellow and an ELATES Fellow. She is a recipient of ICSE 2026 Most Influential Paper Award, ICSE 2026 retrospective Most Influential SEIP Paper Award, an Early Career Academic Achievement Alumni Award from the University of Illinois, Urbana-Champaign, Canada Research Chair, and multiple industry awards. Dr. Tan’s co-authored papers have received Best Paper Award Finalist at ICRA 2025; ACM Distinguished Paper Awards at CCS 2024, ASE 2020, MSR 2018, and FSE 2016; Spotlight at NeurIPS 2025; Oral at AAAI 2023; and IEEE Micro’s Top Picks in 2006. She has served as Program Co-Chair of FSE 2024 and LLM4Code, Associate Editor of IEEE Transactions on Software Engineering and Empirical Software Engineering, and ACM SIGSOFT Treasurer and elected Member-at-Large.