Author

Xintao Wang

Observed name: Wang, Xintao

Institutions: Johns Hopkins University, University of Macau, Fudan University, UNSW Sydney, RIKEN, RIKEN Center for Advanced Intelligence Project, The University of Tokyo, Carnegie Mellon University

Observed institutions: Johns Hopkins University, University of Macau, Fudan University, UNSW Sydney, RIKEN, RIKEN Center for Advanced Intelligence Project, The University of Tokyo, Carnegie Mellon University

OpenAlex ID: A5153407648

RGDT-Bench: Benchmarking LLM Reasoning for Rule-Governed Decisions and Their Justifications

2026 · Zhao, Jianpeng, Xu, Haihua, et al. · arXiv (Cornell University)

Beyond Skill Evolution: Self-Evolving Context Management Policies for Long-Horizon Agent Harnesses

2026 · Li, Weiyuan, Xu, Jinghan, et al. · arXiv (Cornell University)

On the Behavioral Traits of LLM Agents

2026 · Zhao, Haokai, Gao, Jie, et al. · arXiv (Cornell University)

Works count: 3

Citation count:

H-index:

I10-index: