arXiv cs.AI· Qingqing Wang, Liqiang Xiao, Chang Chang·· 13 小时前AI 评分31
基于 Qwen3-14B 的证据驱动多智能体复合 AI 系统，用于头颈质子放疗计划
An Evidence-Driven Multi-Agent Compound AI System for Head and Neck Proton Radiotherapy Planning
AI 导读
研究团队构建了一套证据驱动的多智能体复合 AI 系统，将基于 PPO 的 DRL 自动计划与基于 LLM 的对话式计划优化结合，用于质子 PBS 头颈癌放疗。系统由规划智能体、聊天机器人和评估智能体组成，其中规划智能体基于 Qwen3-14B，经 SFT 与 GRPO 后训练，在指令遵循、信息检索和领域推理上优于基座模型。
正文 · 原文
Abstract:Radiation treatment planning requires balancing competing objectives to satisfy clinical criteria while accommodating physicians' preferences. This study aims to develop an evidence-driven, multi-agent compound AI system that integrates DRL-based automated treatment planning with LLM-based conversational plan refinement for proton PBS therapy. A policy network trained using PPO first generates multiple plans without human intervention, from which one is selected as the target plan and the others serve as references for subsequent refinements. For challenging cases requiring further adjustments, an LLM-based multi-agent system enables plan refinement through natural language interactions. The system comprises a planning agent that recommends evidence-supported adjustments, a chatbot providing a unified conversational interface, and an evaluation agent that retrieves clinical metrics and identifies constraint violations. To enhance domain-specific reasoning, the planning agent based on Qwen3-14B is designed to justify its recommendations using evidence from previously generated plans and post-trained on task-specific data using SFT and GRPO. The framework was trained and evaluated using 21 patients with H&N cancers, with 5 PPO-generated plans per patient. Of these, 50 plans were selected for instruction-guided refinement. Compared with the base LLM, the post-trained Qwen3-14B demonstrated improved instruction-following, information retrieval and domain-specific reasoning capabilities. The resulting adjustments more effectively improved user-prioritized objectives while limiting deterioration in competing objectives, yielding more clinically appropriate trade-offs in patient-specific plan refinement. The proposed compound AI system provides a user-friendly planning platform, offering a promising approach to personalized proton PBS treatment planning.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.29010 [cs.AI] |
| (or arXiv:2610.29010v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.29010 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Qingqing Wang [view email]
[v1]
Wed, 21 Oct 2026 00:21:19 UTC (1,257 KB)
来源：arXiv cs.AI · arxiv.org