Skip to main content
Search

# RadOnc-Agent

1 related articles

Subscribe to updates
  1. arXiv

    RadOnc-Agent splits radiotherapy into four phases and 26 callable functions, hitting the intended function in 98.79% of single-function executions

    The work presents RadOnc-Agent, an agentic framework that formalizes radiotherapy into four clinical phases and exposes 26 callable functions through a conversational interface, with a large-language-model controller mapping clinical intent to schema-constrained calls while preserving patient and workflow context; across 2,600 single-function requests, 200 prespecified synthetic cross-stage scenarios, and 120 workflow instances from 60 de-identified patient records, it 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.

You’re all caught up