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

Yang Xu

5 indexed papers

Recent (6 mo)
5
With code
0
Influential cites
0
Benchmarked
0

Publications per year

5
26

Top categories

ML×2Software Eng.×2AI×2Info Retrieval×1Sound×1Multimedia×1NLP×1

Frequent co-authors

Yi Zhang3×
Fei Huang2×
Xiaoyi Chen2×
Yifei Gao2×
Xingxing Song2×
Jitao Sang2×

Research Timeline

2026
GUITestScape: Towards Open-set Evaluation on Exploratory GUI Testing

The paper introduces GUITestScape, a comprehensive benchmark for exploratory GUI testing, and GUIJudge, an open-set evaluator that significantly improves the assessment of AI agents' defect detection capabilities.

GUITestScape: Towards Open-set Evaluation on Exploratory GUI Testing

The paper introduces GUITestScape, a comprehensive benchmark for exploratory GUI testing, and GUIJudge, an open-set evaluator that significantly improves the assessment of AI agents' defect detection capabilities.

Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling

The paper presents Bebop, a method to improve the rollout stage in reinforcement learning by optimizing Multi-Token Prediction (MTP) acceptance rates.

Beyond Artifacts: Towards Generalizable Synthetic Song Detection via Music-Intrinsic Features

This paper proposes a flexible framework called Sofia for reliable Synthetic Song Detection (SSD) using music-intrinsic attributes and an adaptive Mixture-of-Experts module.

MagicSelector: Joint Optimization for Agent Tool Selection via Counterfactual Decomposition and Progressive Reranking

MagicSelector is a framework for tool retrieval in agents using counterfactual task decomposition, progressive reranking, and dynamic Top-K.

Highlighted terms show continued research focus across papers

Papers

cs.IREmpiricalRecentJul 20, 2026

MagicSelector: Joint Optimization for Agent Tool Selection via Counterfactual Decomposition and Progressive Reranking

HONOR Agentic Search Team, Zhengzong Chen, Lei Tang, Lijun Liu +26 more

MagicSelector is a framework for tool retrieval in agents using counterfactual task decomposition, progressive reranking, and dynamic Top-K.

View →
cs.SDcs.LGcs.MMEmpirical
Recent
Jun 15, 2026

Beyond Artifacts: Towards Generalizable Synthetic Song Detection via Music-Intrinsic Features

Yan Han, Zhibin Wen, Yuan Wang, Shuangrun Shao +3 more

This paper proposes a flexible framework called Sofia for reliable Synthetic Song Detection (SSD) using music-intrinsic attributes and an adaptive Mixture-of-Experts module.

View →
cs.LGcs.CLEmpiricalRecentJun 10, 2026

Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling

Yucheng Li, Huiqiang Jiang, Yang Xu, Jianxin Yang +13 more

The paper presents Bebop, a method to improve the rollout stage in reinforcement learning by optimizing Multi-Token Prediction (MTP) acceptance rates.

View →
cs.SEcs.AIRecentMay 28, 2026

GUITestScape: Towards Open-set Evaluation on Exploratory GUI Testing

Xiaoyi Chen, Yifei Gao, Yang Xu, Xingxing Song +2 more

The paper introduces GUITestScape, a comprehensive benchmark for exploratory GUI testing, and GUIJudge, an open-set evaluator that significantly improves the assessment of AI agents' defect detection…

View →
cs.SEcs.AIRecentMay 28, 2026

GUITestScape: Towards Open-set Evaluation on Exploratory GUI Testing

Xiaoyi Chen, Yifei Gao, Yang Xu, Xingxing Song +2 more

The paper introduces GUITestScape, a comprehensive benchmark for exploratory GUI testing, and GUIJudge, an open-set evaluator that significantly improves the assessment of AI agents' defect detection…

View →