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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Qin, Lang, Gan, Zijian, Cao, Xu, Jiang, Pengcheng, Jiang, Yankai, Han, Jiawei, Wu, Kaishun, Chen, Jintai
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914095839576064
author Qin, Lang
Gan, Zijian
Cao, Xu
Jiang, Pengcheng
Jiang, Yankai
Han, Jiawei
Wu, Kaishun
Chen, Jintai
author_facet Qin, Lang
Gan, Zijian
Cao, Xu
Jiang, Pengcheng
Jiang, Yankai
Han, Jiawei
Wu, Kaishun
Chen, Jintai
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_05764
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RareAgent: Self-Evolving Reasoning for Drug Repurposing in Rare Diseases
Qin, Lang
Gan, Zijian
Cao, Xu
Jiang, Pengcheng
Jiang, Yankai
Han, Jiawei
Wu, Kaishun
Chen, Jintai
Artificial Intelligence
Multiagent Systems
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.
title RareAgent: Self-Evolving Reasoning for Drug Repurposing in Rare Diseases
topic Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2510.05764