AI system combines reinforcement learning and LLMs for radiotherapy planning

Researchers have developed a novel multi-agent AI system that combines deep reinforcement learning with large language models to optimize proton radiotherapy planning for head and neck cancer patients. The system first generates multiple treatment plans using Proximal Policy Optimization, then refines the selected plan through natural language interaction with a Qwen3-14B based planning agent. This approach aims to improve clinical outcomes by better balancing competing objectives and incorporating physician preferences, demonstrating enhanced instruction-following and domain-specific reasoning compared to a base LLM. AI

IMPACT This research could lead to more personalized and effective cancer treatment planning by improving the efficiency and accuracy of radiotherapy.

RANK_REASON The cluster contains an academic paper detailing a new AI system and its evaluation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• deep reinforcement learning
• Grpo
• H&N
• Proximal Policy Optimization
• Qwen3 14B
• supervised fine-tuning

• paper
• model release
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →