Author

Mingxi Wang

Observed name: Wang, Mingxi

Institution: University of Southern California

Observed institution: University of Southern California

OpenAlex ID: A5146971864

SynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement Learning

2026 · Yang, Wei, Li, Shawn, et al. · arXiv (Cornell University) · 1

Foundation-Model-Assisted Reward Design for Reinforcement Learning: A Review of Reward Program Synthesis, Multimodal Feedback, and Trustworthiness

2026 · Wei Zhu, Jinyin Bai, et al. · Information

Works count: 2

Citation count: 1

H-index: 1

I10-index: