OralGPT-Plus：通过强化学习学会使用视觉工具进行全景 X 光分析
OralGPT-Plus: Learning to Use Visual Tools via Reinforcement Learning for Panoramic X-ray Analysis
把「调用视觉工具做局部复查 + 对侧对称比较」建模成可学习的多步推理策略，并用 rubric 奖励与诊断驱动奖励稳定长程强化学习，这套 agentic 交互范式可迁移到任何需要细粒度空间核查的视觉语言模型任务（如病灶定位、遥感判读）。
原文依据 an agentic vision-language model designed to perform iterative and symmetry-aware diagnostic reasoning
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论全景牙科 X 光片需要细粒度空间推理、双侧对称性理解以及多步诊断验证，然而现有的视觉语言模型在静态单次推理范式下运行，限制了其临床可靠性。本文提出 OralGPT-Plus，一种智能体式视觉语言模型，旨在为全景牙科 X 光片分析执行迭代式、对称性感知的诊断推理。为支撑该范式，我们构建了 DentalProbe，一个包含五千张图像的数据集，配有专家整理的诊断轨迹，为局部检查与对侧比较提供结构化监督。我们进一步提出一种以复查为驱动的强化学习框架，通过基于评分细则的奖励与条件化的诊断驱动奖励，鼓励具有临床意义的复查行为并稳定长程推理。同时，我们提出 MMOral-X，首个面向整体全景诊断的基准，包含 300 道开放式问题以及跨多个难度等级的区域级标注。OralGPT-Plus 在 MMOral-X 与既有全景基准上相较强基线取得一致且可靠的提升，表明交互式与对称性引导推理的有效性。本工作凸显了智能体建模在牙科影像中的价值，并为未来临床对齐的全景 X 光片分析研究提供了基础。
英文原文摘要 1466 字符
Panoramic dental radiographs require fine-grained spatial reasoning, bilateral symmetry understanding, and multi-step diagnostic verification, yet existing vision-language models operate under a static single-pass paradigm that limits their clinical reliability. In this paper, we introduce OralGPT-Plus, an agentic vision-language model designed to perform iterative and symmetry-aware diagnostic reasoning for panoramic dental radiograph analysis. To support this paradigm, we construct DentalProbe, a five-thousand-image dataset with expert-curated diagnostic trajectories that provide structured supervision for localized inspection and contralateral comparison. We further develop a Reinspection-driven reinforcement learning framework that encourages clinically meaningful re-examination and stabilizes long-horizon reasoning with rubric-based reward and conditioned diagnostic-driven reward. In parallel, we present MMOral-X, the first benchmark for holistic panoramic diagnosis, containing 300 open-ended questions and region-level annotations across multiple difficulty levels. OralGPT-Plus demonstrates consistent and reliable improvements over strong baselines on MMOral-X and established panoramic benchmarks, indicating the effectiveness of interactive and symmetry-informed reasoning. Our work highlights the value of agentic modeling for dental imaging and provides a foundation for future research in clinically aligned panoramic radiograph analysis.