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

Liang Cheng

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

AI×2Probability×1ML×1Systems and Control×1Optimization and Control×1Stats ML×1

Frequent co-authors

Mingsheng Cai2×
Jiuming Jiang2×
Luo Mai2×
Hao Liang1×
Cheng Tang1×
Yunzong Xu1×

Research Timeline

2026
Do Agents Know What They Can't Do? Evaluating Feasibility Awareness in Tool-Using Agents

The paper proposes FeasiGen, a method to automatically create infeasible tasks for tool-using agents, and finds that most current agents struggle significantly to detect and stop when faced with such impossible tasks.

Do Agents Know What They Can't Do? Evaluating Feasibility Awareness in Tool-Using Agents

The paper proposes FeasiGen, a method to automatically create infeasible tasks for tool-using agents, and finds that most current agents struggle significantly to detect and stop when faced with such impossible tasks.

Finite-Time Queue Peak Laws in Stochastic Networks: Logarithmic Scaling After Geometric Thresholds

This paper studies finite-horizon queue peaks in generalized switches and provides new bounds and insights.

Highlighted terms show continued research focus across papers

Papers

math.PRcs.LGeess.SYTheoreticalRecentJun 16, 2026

Finite-Time Queue Peak Laws in Stochastic Networks: Logarithmic Scaling After Geometric Thresholds

Hao Liang, Cheng Tang, Yunzong Xu

This paper studies finite-horizon queue peaks in generalized switches and provides new bounds and insights.

View →
cs.AIRecentMay 27, 2026

Do Agents Know What They Can't Do? Evaluating Feasibility Awareness in Tool-Using Agents

Liang Cheng, Mingsheng Cai, Jiuming Jiang, Luo Mai

The paper proposes FeasiGen, a method to automatically create infeasible tasks for tool-using agents, and finds that most current agents struggle significantly to detect and stop when faced with such…

View →
cs.AIRecentMay 27, 2026

Do Agents Know What They Can't Do? Evaluating Feasibility Awareness in Tool-Using Agents

Liang Cheng, Mingsheng Cai, Jiuming Jiang, Luo Mai

The paper proposes FeasiGen, a method to automatically create infeasible tasks for tool-using agents, and finds that most current agents struggle significantly to detect and stop when faced with such…

View →