Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early Detection

It outperforms nine baselines, particularly in never-smoker populations, by integrating an Experience Pool and multi-agent reinforcement learning for optimized patient context retrieval and collaboration.

Key Points

• Utilizes an Experience Pool for non-parametric memory and few-shot context retrieval.
• Employs multi-agent reinforcement learning to optimize collaboration between agents.
• Achieves superior performance on lung cancer prediction tasks over nine strong baselines.
• Demonstrates improved specificity and sensitivity in risk prediction through complementary mechanisms.
• Highlights the importance of verified patient data for enhancing temporal reasoning in agents.