Portrait of Hyeokmin Kwon

Hyeokmin Kwon

Undergraduate researcher working across AI interaction and software engineering.

Currently an intern researcher at the Ultimate Interface Lab, UNIST, studying AI interaction under Prof. Seongkook Heo.

About

I'm a Computer Science student at Handong Global University, working at the intersection of software engineering and human-computer interaction.

Most recently, I've been researching AI interaction as an undergraduate intern at the Ultimate Interface Lab, UNIST, advised by Prof. Seongkook Heo — looking at how people interact with AI agents, with a particular interest in accessibility.

Before that, my research centered on intelligent software engineering: LLM-based program repair, code graphs, and developer agents. I like taking a problem from its research question to a working system — designing the architecture, building the feedback loop, and learning from where it breaks.

Education

Mar. 2021 – Present

Handong Global University

B.S. in Computer Science, Advanced Major in AI Computer Science — Pohang, Republic of Korea

Relevant Coursework: Data Structures, Algorithms, Operating Systems, Database Systems, Machine Learning, Software Engineering, Compiler Theory

Jan. 2020 – Dec. 2020

University of Cape Town

Finance with Accounting — Cape Town, South Africa

Research

AI Interaction — Ultimate Interface Lab, UNIST

As an undergraduate research intern advised by Prof. Seongkook Heo, I study how people interact with AI systems, with a focus on accessibility — exploring interaction techniques and interfaces that make AI agents easier and more equitable to use.

Software Engineering — Intelligent Software Engineering Lab, HGU

As an undergraduate researcher in the Intelligent Software Engineering Lab, advised by Prof. Jae Chang Nam, I studied automated software engineering, code graph analysis, and AI/ML environment automation. I also contributed to static-analysis-based malware detection research in collaboration with UMV.

AI Interaction & Accessibility
LLM-based Automated Program Repair
Code Graphs & Program Analysis
AI Agents for Software Engineering

Publications

KCSE 2026 Full Paper Best Paper Award

A Survey on Leveraging Code Graphs for LLM-based Automated Program Repair

Shinyeob Kang, Jikwang Lee, Hyeokmin Kwon, Jaechang Nam. KCSE 2026 Proceedings, p. 170.

KCSE 2026 Short Paper

EnvAgent: Automated Conda Environment Building System for AI/ML Projects

Hyeokmin Kwon, Jikwang Lee, Shinyeob Kang, Yongbean Chung, Jaechang Nam. KCSE 2026 Proceedings, p. 198.

Projects

EnvAgent

An LLM-based agent that analyzes source imports, dependency files, and installation logs to generate and iteratively repair Conda environments.

LLM AgentsASTPythonConda

Static Malware Detection

Research into static-analysis features and benchmark pipelines for Linux ELF, Windows PE, PDF, Word, and Excel malware.

Static AnalysisLightGBMSecurity

High-Availability CCTV Events

An MQTT delivery system with active/backup failover, QoS 1, store-and-forward, RTT-based routing, and duplicate filtering.

MQTTFault ToleranceIoT

Maritime Drowning Detection

A LoRa sensing network with multi-hop relay, ACK-based delivery, CRC validation, and a real-time FastAPI dashboard.

LoRaESP32FastAPI

Experience

Aug. 2026 — Present

Ultimate Interface Lab, UNIST

Undergraduate Research Intern · Advised by Prof. Seongkook Heo · AI Interaction & Accessibility

Jun. 2026 — Present

Seoul National University AI Big Data Fintech Program

Trainee, 13th Cohort

Mar. — Jun. 2026

Malware Detection Modeling Research

Research Assistant · Collaboration with UMV

Dec. 2024 — Jun. 2026

Intelligent Software Engineering Lab

Undergraduate Researcher · Handong Global University

Mar. — Jun. 2025

Java Programming

Teaching Assistant · Handong Global University

Awards

Jul. 2026

Encouragement Award

Google AI Agent Program & Competition · Context Guard

Jun. 2026

Excellence Award

Capstone Festival · Mitigating AI Hallucination

Feb. 2026

Best Paper Award

KCSE 2026 · Code Graphs for LLM-based APR Survey

Nov. 2025

Grand Prize

Upstage AI Agent Hackathon · EnvAgent using n8n

Nov. 2025

Grand Prize & Excellence Award

Software Festival, Convergence Track · Vintan and Juum

Skills

ProgrammingPython, Java, C/C++, SQL, Bash
Frameworks & ToolsGit, Docker, Linux, Conda, MySQL, Spring Boot, FastAPI, Flask
AI & DataOpenAI API, LLM Prompting, LightGBM, scikit-learn, Feature Engineering
Systems & SecurityStatic Analysis, Malware Detection, MQTT, LoRa, Raspberry Pi, ESP32
LanguagesKorean (Native), English (Professional Working Proficiency · OPIc IH · New TEPS 412)