Get started
Author

Xiyang Hu

Observed name: Hu, Xiyang
Observed institution: Arizona State University
ORCID: 0000-0001-7269-3828
Observed ORCID: 0000-0001-7269-3828
OpenAlex ID: A5136056694
Counterfactual Trace Auditing of LLM Agent Skills
2026 · Zhou, Xiaolin, Liu, Jinbo, et al. · arXiv (Cornell University) · 11
PDF
When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents
2026 · Zhou, Xiaolin, Yuan, Aojie, et al. · arXiv (Cornell University) · 5
PDF
The Sim-to-Real Gap of Foundation Model Agents: A Unified MDP Perspective
2026 · Xiaoou Liu, Tiejin Chen, et al. · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · 2
WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks
2026 · Prince Zizhuang Wang, Aojie Yuan, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 2
PDF
CUA-SWE: When Computer-Use Agents Meet Visual Software Engineering
2026 · Wang, Prince Zizhuang, Liang, Chenhao, et al. · arXiv (Cornell University)
PDF
Are LLMs Reliable Rankers? Rank Manipulation via Two-Stage Token Optimization
2026 · Association for Computational Linguistics 2026, Du, Yixuan, et al. · Underline Science Inc.
Lost in Execution: On the Multilingual Robustness of Tool Calling in Large Language Models
2026 · Association for Computational Linguistics 2026, Hu, Xiyang, et al. · Underline Science Inc.
Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs
2026 · Association for Computational Linguistics 2026, Cao, Defu, et al. · Underline Science Inc.
Works count: 8
Citation count: 20
H-index: 2
I10-index: 1
Year
Topic
Type