Cura 1T是专为医疗代理设计的大型语言模型，支持诊疗全流程。
Cura 1T: Specialized Model for Agentic Healthcare
- 通过人类引导的递归自改进循环训练，持续优化多任务能力。
- 在医疗评估中表现顶尖，且保持跨领域推理竞争力。
- 适合医疗智能助手、临床决策支持系统研发者使用。
医疗AI代理需完成患者问诊、文本与图像的临床推理、交互式诊断及电子病历工具使用，但能整合这些场景的专用代理模型仍稀缺。各项能力常因单一优化而相互干扰。本文提出Cura 1T，基于开源模型Kimi-K2.6构建，采用人类引导的递归自改进（RSI）循环进行训练。每轮迭代中，RSI规划目标能力，训练模型，评估基准轨迹，并根据失败情况，通过针对性合成与精选样例动态调整数据混合，而非单一通用医学数据更新。在医疗评估套件中，Cura 1T排名处于前沿水平，同时在域外推理和代理基准上保持竞争力。
原文摘要 · Abstract (English)
Healthcare AI agents handle patient consultation, clinical reasoning over text and images, interactive diagnosis, and electronic health record (EHR) tool use, yet specialized agentic models that cover these use cases together remain limited. These capabilities fail in different ways, and a narrow update for one task can degrade another. We present Cura 1T, a healthcare-specialized LLM built on the open-weight Kimi-K2.6 and trained through a human-gated recursive self-improvement (RSI) loop. Specifically, in each round, the RSI harness plans a target capability, trains the model, evaluates benchmark trajectories, and refines the data mixture from observed failures with targeted synthetic and curated examples rather than a single generic medical-data update. Across the healthcare evaluation suite, Cura 1T ranks at or near the top among frontier baselines while remaining competitive on out-of-domain reasoning and agentic benchmarks.
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。