Vision-language models (VLM) have markedly advanced AI-driven interpretation and reporting of complex medical imaging, such as computed tomography (CT). Yet, existing methods largely relegate clinicians to passive observers of final outputs, offering no interpretable reasoning trace for them to inspect, validate, or refine. To address this, we introduce RadAgent, a tool-using AI agent that generates CT reports through a stepwise and interpretable process. Each resulting report is accompanied by a fully inspectable trace of intermediate decisions and tool interactions, allowing clinicians to examine how the reported findings are derived. In our experiments, we observe that RadAgent improves Chest CT report generation over its 3D VLM counterpart, CT-Chat, across three dimensions. Clinical accuracy improves by 6.0 points (36.4% relative) in macro-F1 and 5.4 points (19.6% relative) in micro-F1. Robustness under adversarial conditions improves by 24.7 points (41.9% relative). Furthermore, RadAgent achieves 37.0% in faithfulness, a new capability entirely absent in its 3D VLM counterpart. By structuring the interpretation of chest CT as an explicit, tool-augmented and iterative reasoning trace, RadAgent brings us closer toward transparent and reliable AI for radiology.

翻译：[翻译后的摘要在中文] 视觉-语言模型推动了对复杂医学影像（如计算机断层扫描）的AI驱动解读与报告生成。然而，现有方法大多将临床医生置于最终输出的被动观察者角色，无法提供可解释的推理过程供其检查、验证或修正。为解决这一问题，我们提出RadAgent——一种使用工具的AI智能体，通过逐步且可解释的流程生成CT报告。每份报告均附带完整的中间决策与工具交互可检查轨迹，使临床医生能够审视报告结果的推导过程。实验表明，RadAgent在三个维度上较其3D VLM对应模型CT-Chat显著提升了胸部CT报告生成能力：临床准确性方面，宏F1分数提升6.0分（相对增长36.4%），微F1分数提升5.4分（相对增长19.6%）；对抗条件下的鲁棒性提升24.7分（相对增长41.9%）。此外，RadAgent在忠实度上达到37.0%，这是其3D VLM模型完全不具备的新能力。通过将胸部CT解读构建为显式、工具增强的迭代推理轨迹，RadAgent推动我们迈向透明可靠的放射学AI。