Preprint Alert!
Our RL-trained RadAgent turns CT report generation from a black box into an inspectable, step-by-step tool-augmented process, significantly improving accuracy, robustness, and faithfulness over 3D vision language models.
Preprint: https://t.co/CbjPDEi65I
Page: https://t.co/cxdb7bN3T7
Code: https://t.co/qnSxn3BUYd
Big thanks to a stellar team of co-authors @de_Jiung@TomaszSternal@KStyppa@thoefler! @ETH_en
1/