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.

翻译：罕见疾病的计算药物重定位在药物与目标疾病间缺乏先验关联时尤为困难。此时知识图谱补全与消息传递图神经网络缺乏可靠信号进行学习与传播，导致性能低下。本文提出RareAgent——一种自演进多智能体系统，将此项任务从被动模式识别重构为主动证据搜寻式推理。该系统通过组织任务导向的对抗性辩论，使智能体从多元视角动态构建证据图谱，用以支持、反驳或推导假设。推理策略在自演进循环中进行事后分析，生成优化智能体策略的文本反馈，同时将成功推理路径提炼为可迁移启发式规则以加速后续研究。综合评估表明，RareAgent将适应症AUPRC指标较基线推理方法提升18.1%，并提供与临床证据一致的透明推理链。