RareAgent: Self-Evolving Reasoning for Drug Repurposing in Rare Diseases

作者：Lang Qin, Gan, Zijian, Xu Cao, Pengcheng Jiang, Jiang, Yankai, Han, Jiawei, Kaishun Wu, Jintai Chen · 发表于：arXiv (Cornell University) · 年份：2025 · DOI：10.48550/arxiv.2510.05764 · 被引用次数：1 · 研究领域：Topic Modeling、Biomedical Text Mining and Ontologies、Natural Language Processing Techniques

Computational drug repurposing for rare diseases is especially challenging when no prior associations exist between drugs and target diseases. Therefore, knowledge graph completion and message-passing GNNs have little reliable signal to learn and propagate, resulting in poor performance. We present RareAgent, a self-evolving multi-agent system that reframes this task from passive pattern recognition to active evidence-seeking reasoning. RareAgent organizes task-specific adversarial debates in which agents dynamically construct evidence graphs from diverse perspectives to support, refute, or entail hypotheses. The reasoning strategies are analyzed post hoc in a self-evolutionary loop, producing textual feedback that refines agent policies, while successful reasoning paths are distilled into transferable heuristics to accelerate future investigations. Comprehensive evaluations reveal that RareAgent improves the indication AUPRC by 18.1% over reasoning baselines and provides a transparent reasoning chain consistent with clinical evidence.