Get started
Author

Haoran Xi

Observed name: Xi, Haoran
ORCID: 0009-0005-3268-7366
Observed ORCIDs: 0009-0005-3268-7366, 0009-0009-3051-1630
OpenAlex ID: A5101377025
EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities
2024 · Abramovich, Talor, Udeshi, Meet, et al. · arXiv (Cornell University) · 70
PDF
ARVO: Atlas of Reproducible Vulnerabilities for Open-Source Software
2026 · Xiang Mei, Jordi Del Castillo, et al. · IEEE European Symposium on Security and Privacy · 52
PDF
D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive Security
2025 · Udeshi, Meet, Shao, Minghao, et al. · arXiv (Cornell University) · 29
PDF
Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark
2026 · Minghao Shao, Nanda Rani, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 13
From Trace to Line: An Empirical Study of What Drives LLM-Based OSS Vulnerability Localization
2026 · Haoran Xi, Minghao Shao, et al. · IEEE Access · 7
How Do LLM Agents Actually Get the Flag? Trace-Level Provenance for Agentic Offensive Security Evaluation
2026 · Milner, Kimberly, Shao, Minghao, et al. · arXiv (Cornell University) · 4
PDF
CTFExplorer: Evaluating LLM Offensive Agents Through Multi-Target Web CTF Benchmarking
2026 · Rani, Nanda, Milner, Kimberly, et al. · arXiv (Cornell University) · 4
PDF
AI In Cybersecurity Education -- Scalable Agentic CTF Design Principles and Educational Outcomes
2026 · Xi, Haoran, Shao, Minghao, et al. · arXiv (Cornell University) · 1
PDF
Learning to Curate What You Generate for Generalizable Few-Shot Class-Incremental Learning
2026 · Junhui Yin, Yuchen Yang, et al. · ACM International Conference on Multimedia (ACM MM)
460 - Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark
2026 · Association for Artificial Intelligence 2026, Aggarwal, Saksham, et al. · Underline Science Inc.
Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark
2026 · Association for Artificial Intelligence 2026, Aggarwal, Saksham, et al. · Underline Science Inc.
Works count: 13
Citation count: 307
H-index: 7
I10-index: 6
Year
Topic
Type