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

Shuhuai Li

2 indexed papers

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

Publications per year

2
26

Top categories

Distributed×1AI×1

Frequent co-authors

Shengdong Ye1×
Dongdong Ge1×
Yinyu Ye1×
Jianghao Lin1×
Pin Qian1×
Su Wang1×

Research Timeline

2026
Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAG

The paper introduces FORCEBENCH, a new stress test designed to evaluate whether cited sources genuinely warrant the strength of a claim, revealing that standard citation evaluation methods often fail to detect over-strong claims.

TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving

This paper presents TAO, a tool-aware joint scheduling framework for LLM-based agentic serving that reduces latency, mean time to first token, and increases decode throughput.

Highlighted terms show continued research focus across papers

Papers

cs.DCEmpiricalRecentOct 27, 2026

TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving

Shuhuai Li, Shengdong Ye, Dongdong Ge, Yinyu Ye +1 more

This paper presents TAO, a tool-aware joint scheduling framework for LLM-based agentic serving that reduces latency, mean time to first token, and increases decode throughput.

View →
cs.AIRecentMay 27, 2026

Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAG

Pin Qian, Su Wang, Xiaoyuan Wang, Yihang Chen +6 more

The paper introduces FORCEBENCH, a new stress test designed to evaluate whether cited sources genuinely warrant the strength of a claim, revealing that standard citation evaluation methods often fail…

View →