Cura 1T: Specialized Model for Agentic Healthcare
Quick Answer
This paper shows that Cura 1T is a healthcare-specialized LLM that utilizes a human-gated self-evolution loop to enhance capabilities in patient consultation, clinical reasoning, and EHR tool use.
Quick Take
It ranks at or near the top in healthcare evaluations while maintaining competitiveness in out-of-domain reasoning and agentic benchmarks.
Key Points
- Cura 1T is trained through a targeted data-centered evolution loop.
- The model excels in handling high-stakes healthcare communication and workflows.
- It ranks at or near the top among frontier baselines in healthcare evaluations.
- Cura 1T improves through synthetic and curated examples rather than generic updates.
- It remains competitive in out-of-domain reasoning tasks.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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.
| Comments: | Model: this https URL Docs: this https URL Github: this https URL |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.15314 [cs.AI] |
| (or arXiv:2607.15314v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.15314 arXiv-issued DOI via DataCite |
Submission history
From: Haolin Chen [view email]
[v1]
Wed, 15 Jul 2026 22:05:23 UTC (1,388 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.