RareAgent通过多智能体辩论实现药物重定位的自进化推理。
RareAgent: Self-Evolving Reasoning for Drug Repurposing in Rare Diseases
- 用多智能体对抗性辩论动态构建证据图支持假设
- 比基线方法提升18.1%的指示AUPRC指标
- 输出可解释推理链，适合临床验证场景
罕见病的计算药物重定位在缺乏药物与疾病先验关联时尤为困难，导致知识图谱补全和消息传递GNN难以获取可靠信号，性能不佳。我们提出RareAgent，一种自进化多智能体系统，将任务从被动模式识别转变为积极的证据探寻推理。RareAgent组织特定任务的对抗性辩论，各智能体从不同角度动态构建证据图以支持、反驳或推导假说。事后对推理策略进行分析，通过自进化循环生成文本反馈以优化智能体策略，同时将成功推理路径提炼为可迁移启发式规则，加速后续研究。全面评估显示，RareAgent在指示AUPRC上较推理基线提升18.1%，并提供与临床证据一致的透明推理链。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。