Author

Di Ma

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Generating Biomedical Fact-Checking Reports with RL-Enhanced Agentic Search

The Evidence-Grounded Group Relative Policy Optimization (EG-GRPO) is proposed to perform reinforcement learning on BioCheck Agent with a task-specific reward that incentivizes advanced search behavior and high-quality evidence retrieval while penalizing hallucinations.

Jiongxiao Wang, Di Ma, Chaoqun Ni · 0 citations