RESEARCH · RESEARCH · #2468
Evidence-driven multi-agent AI (DRL + LLM) for head & neck proton PBS radiotherapy planning (arXiv:2610.29010v1)
This arXiv preprint proposes a compound AI system that combines a PPO-trained policy network to generate multiple proton PBS treatment plans with an LLM-based multi-agent conversational refinement layer. The planning agent (based on Qwen3-14B and post-trained with SFT and GRPO), a chatbot interface, and an evaluation agent were tested on 21 head-and-neck cancer patients (5 PPO plans each; 50 plans selected for instruction-guided refinement), and the post-trained Qwen3-14B improved instruction-following, retrieval and domain reasoning to produce clinically more appropriate trade-offs during user-guided plan adjustments.
KEY POINTS
- This arXiv preprint proposes a compound AI system that combines a PPO-trained policy network to generate multiple proton PBS treatment plans with an LLM-based multi-agent conversational refinement layer.
- The planning agent (based on Qwen3-14B and post-trained with SFT and GRPO), a chatbot interface, and an evaluation agent were tested on 21 head-and-neck cancer patients (5 PPO plans each; 50 plans selected for instruction-guided refinement), and the post-trained Qwen3-14B improved instruction-following, retrieval and domain reasoning to produce clinically more appropriate trade-offs during user-guided plan adjustments.
- Combining DRL-generated candidate plans with an evidence-supporting LLM multi-agent refinement interface could make personalized proton treatment planning faster and more interpretable for clinicians, though results are preliminary (small sample, preprint).
WHY IT MATTERS
Combining DRL-generated candidate plans with an evidence-supporting LLM multi-agent refinement interface could make personalized proton treatment planning faster and more interpretable for clinicians, though results are preliminary (small sample, preprint).