Author

Haohan Wang

Observed name: Wang, Haohan

Institution: University of Illinois Urbana-Champaign

Observed institution: University of Illinois Urbana-Champaign

OpenAlex ID: A5108939203

Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters

2024 · Haibo Jin, Andy Zhou, et al. · neural information processing systems · 8

Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool Primitives

2026 · Jin, Haibo, Wang, Suijin, et al. · arXiv (Cornell University)

SCI-Defense: Detecting Persuasion-Structured Manipulation of LLM-Based Ranking in Generative Engines

2026 · Yu, Xucheng, Jin, Haibo, et al. · arXiv (Cornell University)

TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization

2026 · Fu, Lucheng, Yu, Ye, et al. · arXiv (Cornell University)

Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation

2026 · Yu, Ye, Yuan, Xiaopeng, et al. · arXiv (Cornell University)

Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems

2026 · Yu, Ye, Liu, Heming, et al. · arXiv (Cornell University)

Break Me If You Can: Self-Jailbreaking of Aligned LLMs via Lexical Insertion Prompting

2026 · Kulshreshtha, Devang, Su, Hang, et al. · arXiv (Cornell University)

Works count: 7

Citation count: 8

H-index: 1

I10-index: