{"ID":2832495,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.05576","arxiv_id":"2512.05576","title":"CureAgent: A Training-Free Executor-Analyst Framework for Clinical Reasoning","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.","short_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 a...","url_abs":"https://arxiv.org/abs/2512.05576","url_pdf":"https://arxiv.org/pdf/2512.05576v1","authors":"[\"Ting-Ting Xie\",\"Yixin Zhang\"]","published":"2025-12-05T09:56:58Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\"]","has_code":false,"code_links":[{"ID":606235,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2832495,"paper_url":"https://arxiv.org/abs/2512.05576","paper_title":"CureAgent: A Training-Free Executor-Analyst Framework for Clinical Reasoning","repo_url":"https://github.com/June01/CureAgent","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}