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

Xin Yu

2 indexed papers

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

Publications per year

2
26

Top categories

NLP×1Info Retrieval×1Crypto×1AI×1

Frequent co-authors

Han Zhang1×
Zihao Tang1×
Xiao Liu1×
Yeyun Gong1×
Haizhen Huang1×
Yan Lu1×

Research Timeline

2026
Do Coding Agents Understand Least-Privilege Authorization?

The paper introduces a new benchmark and decomposition method, Sufficiency-Tightness Decomposition, demonstrating that current coding agents struggle to accurately infer least-privilege authorization, and that this decomposition significantly improves both security and task success.

Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory

The paper introduces RHELM, a new benchmark designed to test LLMs' long-term memory by simulating realistic, complex, and evolving dialogues that integrate multiple heterogeneous data sources.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.IRRecentMay 29, 2026

Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory

Han Zhang, Zihao Tang, Xin Yu, Xiao Liu +7 more

The paper introduces RHELM, a new benchmark designed to test LLMs' long-term memory by simulating realistic, complex, and evolving dialogues that integrate multiple heterogeneous data sources.

View →
cs.CRcs.AIRecentMay 14, 2026

Do Coding Agents Understand Least-Privilege Authorization?

Zheng Yan, Jingxiang Weng, Charles Chen, Dengyun Peng +8 more

The paper introduces a new benchmark and decomposition method, Sufficiency-Tightness Decomposition, demonstrating that current coding agents struggle to accurately infer least-privilege authorization,…

View →