RadOnc-Agent: An LLM-Orchestrated Framework for AI Workflows Across the Radiotherapy Care Pathway

查看原文 / View Original 编辑 / Edit

Computer Science > Artificial Intelligence arXiv:2610.06923 (cs) [Submitted on 2 Oct 2026] Title: RadOnc-Agent: An LLM-Orchestrated Framework for AI Workflows Across the Radiotherapy Care Pathway Authors: Caiwen Jiang, Shuoyang Wei, Songlin Zhao, Junyu Li, Jingyuan Chen, Wei Liu.

计算机科学 > 人工智能 arXiv:2610.06923 (cs) [提交于 2026 年 10 月 2 日] 标题：RadOnc-Agent：一种用于放射治疗护理路径中人工智能工作流的大语言模型编排框架作者：Caiwen Jiang, Shuoyang Wei, Songlin Zhao, Junyu Li, Jingyuan Chen, Wei Liu。

Abstract: Artificial intelligence has advanced individual radiotherapy tasks, yet these capabilities remain separated across clinical stages, software environments and data modalities. This fragmentation contrasts with the longitudinal radiotherapy workflow from treatment decision-making through follow-up.

摘要：人工智能已经推动了放射治疗中各项独立任务的发展，但这些能力在临床阶段、软件环境和数据模态之间仍然是割裂的。这种碎片化与从治疗决策到后续随访的纵向放射治疗工作流形成了鲜明对比。

Here we present RadOnc-Agent, an agentic artificial-intelligence framework that formalizes radiotherapy into four clinical phases and provides 26 callable functions through a conversational interface. A large-language-model controller maps clinical intent to schema-constrained calls, preserves patient and workflow context, and routes requests to specialist services.

在此，我们提出了 RadOnc-Agent，这是一个智能体人工智能框架，它将放射治疗形式化为四个临床阶段，并通过对话界面提供 26 个可调用函数。大语言模型控制器将临床意图映射为受模式约束的调用，保留患者和工作流上下文，并将请求路由至专业服务。

We evaluated system execution using 2,600 single-function requests (7,800 repeat executions), 200 prespecified synthetic cross-stage scenarios spanning four phases (600 executions), and 120 workflow instances from 60 de-identified patient records (360 clean executions) representing decision-to-planning and planning-to-adaptation.

我们使用 2,600 个单函数请求（7,800 次重复执行）、跨越四个阶段的 200 个预设合成跨阶段场景（600 次执行），以及来自 60 份去标识化患者记录的 120 个工作流实例（360 次干净执行，代表从决策到计划以及从计划到调整的过程）对系统执行进行了评估。

RadOnc-Agent selected the intended function in 98.79% of single-function executions, completed 96.50% of scripted cross-stage workflows, and completed 96.67% of real-patient workflow executions. In comparative ablations, removing longitudinal state reduced cross-stage completion from 96.50% to 84.00%, while disabling schema and identity validation increased mismatched backend dispatch from 0% to 95.28% in a replay/test evaluation.

RadOnc-Agent 在 98.79% 的单函数执行中选择了预期的函数，完成了 96.50% 的脚本化跨阶段工作流，并完成了 96.67% 的真实患者工作流执行。在对比消融实验中，移除纵向状态使跨阶段完成率从 96.50% 降至 84.00%，而在重放/测试评估中，禁用模式和身份验证导致后端调度不匹配率从 0% 上升至 95.28%。

These findings establish the technical feasibility of an LLM-orchestrated architecture for coordinating heterogeneous radiotherapy capabilities and information across longitudinal workflows; they do not establish clinical correctness, clinical utility or prospective benefit.

这些发现确立了利用大语言模型编排架构来协调纵向工作流中异构放射治疗能力和信息的技术可行性；但它们并未确立临床正确性、临床效用或前瞻性获益。