CureAgent: A Training-Free Executor-Analyst Framework for Clinical Reasoning

TL;DR

CureAgent introduces a modular, training-free framework combining specialized executors and long-context models to improve clinical reasoning, addressing context utilization failure and scaling challenges in biomedical AI.

Contribution

The paper proposes a novel Executor-Analyst modular architecture with stratified ensemble strategies, achieving state-of-the-art performance without finetuning.

Findings

Mitigates reasoning deficits in biomedical LLMs.

Demonstrates the effectiveness of stratified ensemble over global pooling.

Identifies critical scaling insights like context-performance paradox.

Abstract

Current clinical agent built on small LLMs, such as TxAgent suffer from a \textit{Context Utilization Failure}, where models successfully retrieve biomedical evidence due to supervised finetuning but fail to ground their diagnosis in that information. In this work, we propose the Executor-Analyst Framework, a modular architecture that decouples the syntactic precision of tool execution from the semantic robustness of clinical reasoning. By orchestrating specialized TxAgents (Executors) with long-context foundation models (Analysts), we mitigate the reasoning deficits observed in monolithic models. Beyond simple modularity, we demonstrate that a Stratified Ensemble strategy significantly outperforms global pooling by preserving evidentiary diversity, effectively addressing the information bottleneck. Furthermore, our stress tests reveal critical scaling insights: (1) a \textit{Context-Performance Paradox}, where extending reasoning contexts beyond 12k tokens introduces noise that degrades accuracy; and (2) the \textit{Curse of Dimensionality} in action spaces, where expanding toolsets necessitates hierarchical retrieval strategies. Crucially, our approach underscores the potential of training-free architectural engineering, achieving state-of-the-art performance on CURE-Bench without the need for expensive end-to-end finetuning. This provides a scalable, agile foundation for the next generation of trustworthy AI-driven therapeutics. Code has been released on https://github.com/June01/CureAgent.