Huihao Jing

PhD Student · HKUST

I study how to build capable language agents without losing control of safety, privacy, and context.

I am a Computer Science PhD student at the Hong Kong University of Science and Technology. I work with Haoran Li and am advised by Prof. Yangqiu Song in the KnowComp Group.

Google Scholar GitHub Email

Research Interests

LLM Agents

Building and evaluating agents that use tools, memory, and multi-agent workflows.

LLM Safety

Making language models and agents safer, more private, and policy compliant.

Selected publications

2026Preprint

Isolation as a First-Class Principle for LLM-Agent System Safety

Huihao Jing, Wenbin Hu, Shaojin Chen, Haochen Shi, Sirui Zhang, Hanyu Yang, Changxuan Fan, Zhongwei Xie, Hongyu Luo, Wun Yu Chan, Wei Fan, Haoran Li, Yangqiu Song

2026Preprint

PerfCodeBench: Benchmarking LLMs for System-Level High-Performance Code Optimization

Huihao Jing, Wenbin Hu, Haochen Shi, Hanyu Yang, Sirui Zhang, Shaojin Chen, Haoran Li, Yangqiu Song

2025Preprint

MASLegalBench: Benchmarking Multi-Agent Systems in Deductive Legal Reasoning

Huihao Jing, Wenbin Hu, Hongyu Luo, Jianhui Yang, Wei Fan, Haoran Li, Yangqiu Song

2025EMNLP

MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol

Huihao Jing, Haoran Li, Wenbin Hu, Qi Hu, Heli Xu, Tianshu Chu, Peizhao Hu, Yangqiu Song

2025ACL

PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal Compliance

Haoran Li, Wenbin Hu, Huihao Jing, Yulin Chen, Qi Hu, Sirui Han, Tianshu Chu, Peizhao Hu, Yangqiu Song

View all publications

Latest writing

Aug 2026 AI History

Before the Boom

From symbolic AI, backpropagation, and the foundations of deep learning to neural language models, LSTMs, sequence-to-sequence learning, and attention: the technical lineage that led to the Transformer.

Read note

Jul 2026 Notes