arXiv cs.AI· Caiwen Jiang, Shuoyang Wei, Songlin Zhao, Junyu Li, Jingyuan Chen, Yuzhen Ding, Daniel J. Ma, Samir H. Patel, Steven E. Schild, Sujay A. Vora, Wei Liu·· 4 小时前AI 评分33
RadOnc-Agent：覆盖放射治疗全流程的 AI 工作流集成框架
RadOnc-Agent: An Integrated Framework for AI Workflows Across the Radiotherapy Care Pathway
AI 导读
梅奥诊所等机构研究者在 arXiv 发表 RadOnc-Agent，一个通过对话界面连接放疗路径四阶段 17 项阶段特定功能与 9 项通用工具的集成框架，由语言模型控制器将临床意图映射为结构化调用。
正文 · 原文
Authors:Caiwen Jiang, Shuoyang Wei, Songlin Zhao, Junyu Li, Jingyuan Chen, Yuzhen Ding, Daniel J. Ma, Samir H. Patel, Steven E. Schild, Sujay A. Vora, Wei Liu
Abstract:Artificial intelligence has advanced radiotherapy tasks, but these capabilities remain fragmented across the care pathway. Here we present RadOnc-Agent, an integrated framework connecting 17 phase-specific functions and 9 cross-cutting utilities across four phases through a conversational interface. A language-model controller maps clinical intent to structured calls, maintains longitudinal context and validates dispatch. We evaluated request-expression diversity, function coverage, cross-stage composition, information transfer and failure recovery using 2,600 single-function requests (7,800 executions), 200 cross-stage scenarios (600 executions), and 120 workflows from 60 de-identified patient records (360 executions). RadOnc-Agent selected the intended function in 98.79% of single-function executions and completed 96.50% of scripted and 96.67% of real-patient workflows. Removing longitudinal state reduced cross-stage completion from 96.50% to 84.00%; bypassing schema and identity validation increased mismatched dispatch from 0% to 95.28% in replay/test execution. Single-function performance did not by itself predict workflow-level capability. Information continuity and cross-stage dependencies emerged as central constraints. These results establish the technical feasibility of longitudinal integration across radiotherapy workflows and provide a foundation for prospective clinical evaluation.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.06923 [cs.AI] |
| (or arXiv:2610.06923v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.06923 arXiv-issued DOI via DataCite |
Submission history
From: Caiwen Jiang [view email]
[v1]
Fri, 2 Oct 2026 22:39:48 UTC (29,623 KB)
[v2]
Fri, 23 Oct 2026 19:48:50 UTC (28,655 KB)
来源：arXiv cs.AI · arxiv.org