RareAgent: Self-Evolving Reasoning for Drug Repurposing in Rare Diseases
This work addresses drug repurposing for rare diseases, a critical healthcare problem, by offering a novel reasoning approach that overcomes data scarcity, though it is incremental in advancing multi-agent systems for this domain.
The paper tackled the challenge of computational drug repurposing for rare diseases with no prior drug-disease associations, where traditional methods like knowledge graph completion and GNNs perform poorly, by introducing RareAgent, a self-evolving multi-agent system that improved indication AUPRC by 18.1% over reasoning baselines and provided transparent reasoning chains consistent with clinical evidence.
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.