Author

Hengxing Cai

h-index 10 View on Semantic Scholar

We have 2 of 22 papers

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.

#machine learning Mar 2026

SpecXMaster Technical Report

This work proposes SpecXMaster, an intelligent framework leveraging Agentic Reinforcement Learning (RL) for NMR molecular spectral interpretation that enables automated extraction of multiplicity information from both 1H and 13C spectra directly from raw FID (free induction decay) data.

Yu-Tang Ge, Ya-Ning Cui, Han-Zheng Li et al. · arXiv.org · 0 citations

#artificial intelligence Preprint Aug 2026

MedAgent-R1: Faithfulness-Aware Reinforcement Learning for Evidence-Grounded Medical Reasoning

This work identifies a systematic failure mode in RL-trained retrieval agents: outcome-only rewards improve accuracy while degrading faithfulness, a phenomenon the authors term confident hallucination, and addresses this with a faithfulness-gated reward design.

Jiangyuan Chen, Cheng-Hao Zhang, Hengxing Cai · 0 citations