RadOnc-Agent: LLM-Orchestrated Framework Unifies 26 Radiotherapy AI Functions

It is an agentic AI framework that formalizes radiotherapy into four clinical phases and provides 26 callable functions through a conversational interface, where a large language model maps clinical intent to schema-constrained calls and routes them to specialist services.

Existing tools handle individual tasks separated across clinical stages, software environments, and data modalities, whereas RadOnc-Agent links these capabilities into a single longitudinal workflow that preserves patient and workflow context.

No. The results establish technical feasibility of the orchestration architecture only; they do not establish clinical correctness, clinical utility, or prospective benefit, according to the researchers themselves.

It offers an architectural model for unifying fragmented AI tools into longitudinal clinical workflows, relevant to hospitals adopting solutions from multiple vendors, though it remains research-stage rather than deployable.