Search papers, labs, and topics across Lattice.
The paper introduces Cura 1T, a specialized healthcare language model designed to integrate high-stakes communication, expert reasoning, and workflow execution in clinical settings. Utilizing a human-gated self-evolution loop, the model iteratively plans, trains, evaluates, and refines its capabilities based on targeted synthetic and curated examples, addressing the limitations of traditional updates that can degrade performance across tasks. As a result, Cura 1T achieves top rankings in healthcare evaluations while maintaining competitive performance in out-of-domain reasoning and agentic benchmarks.
Cura 1T outperforms existing models in healthcare tasks by leveraging a unique self-evolution training loop that adapts to specific capabilities without sacrificing overall performance.
Healthcare spans high-stakes communication, expert reasoning, and workflow execution, yet specialized LLMs that cover these use cases together remain limited. A healthcare model must handle patient consultation, clinical reasoning over text and images, interactive diagnosis, and electronic health record (EHR) tool use. These capabilities fail in different ways, and a narrow update for one task can degrade another. We present Cura 1T, a healthcare-specialized LLM trained through a human-gated self-evolution loop. In each evolution round, a training agent plans a target capability, trains the model, evaluates benchmark trajectories, and refines the data mixture from observed failures. This data-centered loop improves the model through 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.
