Get started
Author

Hanwen Xing

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
2026 · Li, Xiangyi, Liu, Yimin, et al. · arXiv (Cornell University) · 2
PDF
MatrAIx: Simulating the World with 8.3 Billion Persona Agents
2026 · Li, Xiaomin, Hao, Yuexing, et al. · arXiv (Cornell University) · 1
PDF
PersonaEval: Persona-Based User Simulation for Evaluating Interactive Applications
2026 · Liu, Yifan Simon, Wen, Qianfeng, et al. · arXiv (Cornell University)
PDF
Demystifying Agent Skills: Why They Work-Until They Don't
2026 · Jiang, Zhiyuan, Huang, Fangrui, et al. · arXiv (Cornell University)
PDF
Recipes for Agents: Understanding Skills and Their Open Questions
2026 · Hanwen Xing, Haomin Zhuang, et al. · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)
CurveShift: Is Agent Progress Scalar? Separating Level from Shape
2026 · Xing, Hanwen, Wang, Pengyun, et al. · arXiv (Cornell University)
PDF
OpenThoughts-Agent: Data Recipes for Agentic Models
2026 · Raoof, Negin, Zhuang, Richard, et al. · arXiv (Cornell University)
PDF
AgentClick: A Skill-Based Human-in-the-Loop Review Layer for Terminal AI Agents
2026 · Haomin Zhuang, Hanwen Xing, et al.
ContractBench: Can LLM Agents Preserve Observation Contracts?
2026 · Wang, Jicheng, He, Yifeng, et al. · arXiv (Cornell University)
PDF
AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent Skills
2026 · Zhuang, Haomin, Xing, Hanwen, et al. · arXiv (Cornell University)
PDF
Recipes for Agents: Understanding Skills and Their Open Questions
2026 · Xing, Hanwen, Haomin, Zhuang, et al. · Zenodo (CERN European Organization for Nuclear Research)
A Very Big Video Reasoning Suite
2026 · Wang, Maijunxian, Wang, Ruisi, et al. · arXiv (Cornell University)
PDF
EXACT: Explicit Attribute-Guided Decoding-Time Personalization
2026 · Yu, Xin, Xing, Hanwen, et al. · arXiv (Cornell University)
PDF
Works count: 13
Citation count: 3
H-index: 1
I10-index:
Year
Topic
Type