Hongwei Li
Scholar

Hongwei Li

Google Scholar ID: TODhN38AAAAJ
University of California, Santa Barbara
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
78
 
H-index
4
 
i10-index
2
 
Publications
6
 
Co-authors
0
 
Contact
Emaillihongweiandre@gmail.comCVOpen ↗GitHubOpen ↗
Publications
2 items
OpenSage: Self-programming Agent Generation Engine
2026
Cited
0
DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle
2026
Cited
1
Resume (English only)
Academic Achievements
  • - Publications:
  • - Co-PatcheR: Collaborative Software Patching with Component(s)-specific Small Reasoning Models, NeurIPS 2025
  • - PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification, ICML 2025
  • - BandFuzz: A Practical Framework for Collaborative Fuzzing with Reinforcement Learning, ICSE/SBFT 2024 (Workshop Paper)
  • - Progent: Programmable privilege control for LLM agents, arXiv 2025
  • - FS-IDS: A framework for intrusion detection based on few-shot learning, Computers & Security 2022
  • - Awards:
  • - DARPA AIxCC Finalist (5th Place), won $2 million in semifinal competition
  • - First Place in SBFT 2024 Fuzzing Competition, using BandFuzz framework achieved the best performance across all evaluation metrics
Research Experience
  • - DARPA AIxCC Finalist (5th Place), as a core member of the ARTIPHISHELL team, focusing on automated vulnerability patching and later expanding to custom model fine-tuning for vulnerability detection.
  • - DEF CON CTF 2025 final (11th Place), as a member of the Shellphish team.
  • - SunshineCTF 2021 (11th Place), participated as a solo team in a team-based CTF competition.
Education
  • - University of California, Santa Barbara, Ph.D. in Computer Science, 2024 - Present, Advisor: Dr. Wenbo Guo
  • - Purdue University, Ph.D. in Computer Science (First Year), September 2023 - May 2024
  • - Shanghai Jiao Tong University, Master of Engineering in Electronic Information, September 2020 - June 2023
  • - Shanghai Jiao Tong University, Bachelor of Arts in French & Bachelor of Engineering in Information Engineering, September 2016 - June 2020
Background
  • Research Interests: AI for Security (AI4Sec), reinforcement learning for fuzzing, large language models for automatic patching, software security (vulnerability detection, analysis, and remediation). Professional field: Computer Science. About Me: Ph.D. student at the University of California, Santa Barbara, working under the supervision of Dr. Wenbo Guo, member of the renowned cybersecurity research group Shellphish, and a core member of the ARTIPHISHELL team that competed in the DARPA AI Cyber Challenge (AIxCC).
Miscellany
  • No specific personal interests or hobbies mentioned
Co-authors
0 total
Co-authors: 0 (list not available)