Ph.D. student, School of Computing, KAIST
Dongjae Lee
Formal methods X Agentic AI for Reliable Programming System
I am Dongjae Lee, a Ph.D. student in the School of Computing at KAIST and a member of Prosys Lab, advised by Kihong Heo.
Research Directions
Current questions I am actively exploring.
- Proof-Carrying Spec-Driven Development. I want coding assistants to verify their own code and reduce the amount of human supervision needed for trustworthy software.
- Mixing Natural and Formal Languages. I am interested in programming models that combine LLM-friendly natural language with analyzable formal structure.
- Security for Agentic Software. My work explores how to analyze and secure agentic systems that execute tasks through prompts, tools, and autonomous workflows.
Education
Academic background.
- M.S. in School of Computing, KAIST, South Korea
- B.S. in School of Computing, KAIST, South Korea
Selected Publications
Recent research output.
Honors & Awards
Selected recognitions.
2026
Master's Thesis Excellence Award
2025
Winner
AI Champion Competition
Outstanding Teaching Assistant
CS424 Program Reasoning
2024
B.S. Summa Cum Laude
GPA 4.03/4.3
Finalist
Global AI Idea Lab Contest, CODEGATE
2022-2023
National Excellence Scholarship
2021
Dean's List
Fall 2021
2020
Dean's List
Spring 2020
News
Latest updates from my research and work.
Apr 22, 2026
Expecto accepted
Our paper Expecto was accepted, and I am excited to share the full details and materials here soon.
Read update