Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Hao Ni

Hao Ni

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2ML×1Crypto×1Software Eng.×1

Frequent co-authors

Yifan Bao1×
Xinyu Xi1×
Xinyu Liu1×
Wen Ge1×
Lei Jiang1×
Kevin Zhang1×

Research Timeline

2026
Taint-Style Vulnerability Detection and Confirmation for Node.js Packages Using LLM Agent Reasoning

The paper introduces LLMVD.js, a multi-stage LLM agent pipeline that effectively detects and confirms taint-style vulnerabilities in Node.js packages, achieving significantly higher confirmation rates than traditional program analysis tools.

MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition

MOSAIC introduces a structured agentic framework that treats automated data science as a staged, context-grounded model selection problem, improving performance and traceability over traditional AutoML and unconstrained LLM agents.

Highlighted terms show continued research focus across papers

Papers

cs.AIcs.LGRecentMay 30, 2026

MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition

Yifan Bao, Xinyu Xi, Xinyu Liu, Wen Ge +7 more

MOSAIC introduces a structured agentic framework that treats automated data science as a staged, context-grounded model selection problem, improving performance and traceability over traditional AutoM…

View →
cs.CRcs.AIcs.SERecentApr 22, 2026

Taint-Style Vulnerability Detection and Confirmation for Node.js Packages Using LLM Agent Reasoning

Ronghao Ni, Mihai Christodorescu, Limin Jia

The paper introduces LLMVD.js, a multi-stage LLM agent pipeline that effectively detects and confirms taint-style vulnerabilities in Node.js packages, achieving significantly higher confirmation rates…

View →