Research
Inside χ-Bench’s healthcare workflows
A benchmark for complete healthcare workflows across providers and health plans.
Read the storyNews & Blog
Research, engineering, and ideas from Actava.ai.
Research
How Cura 1T learns through evaluation
How evaluation failures guide training data for a healthcare foundation model.
Read the storyProduct
Training specialized models with Model Factory
How verified workflow experience supports training and checkpoint selection.
Read the storyResources
19 resources
ResourcesResource
ACTAVA | CURA | Huggingface
Χ-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows? χ-Bench evaluates AI agents on end-to-end U.S. healthcare workflows across three long-horizon domains: provider prior authorization, payer utilization management, and population care management. Each task hands the agent a clinical case in a high-fidelity simulator of 20 healthcare apps exposed over MCP, with a 1,279-document Managed-Care Operations Handbook skills, and asks it to drive the case through tool calls and artifact authoring.
ResourcesResource
ACTAVA | CURA | Github
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.
ResourcesResource
ACTAVA | χ-BENCH | arXiv
End-to-end automation of realistic healthcare operations stresses three capabilities underrepresented in current benchmarks: policy density, decisions must be grounded in a large library of medical, insurance, and operational rules; multi-role composition, a single task requires the agent to play multiple roles with handoffs; and multilateral interaction: intermediate workflow steps are multi-turn dialogs, such as peer-to-peer review and patient outreach. We introduce χ -Bench, a benchmark of long-horizon healthcare workflows across three domains: provider prior authorization, payer utilization management, and care management. Each task hands the agent a clinical case in a high-fidelity simulator of 20 healthcare apps exposed via 87 MCP tools, which it must drive to a terminal status through tool calls and writing the role’s artifacts, guided by a 1,279-document managed-care operations handbook skill. Across 30 agent harness/model configurations, the best agent resolves only 28.0% of tasks, no agent clears 20% on strict pass^3, and executing all tasks in a single session slumps the performance to 3.8%. These results raise the hypothesis that similar gaps are likely to surface in other policy-dense, role-composed, irreversible enterprise domains.
ResourcesResource
ACTAVA | CURA | Github
Cura 1T is Actava.ai's one-trillion-parameter healthcare model. Fine-tuned from Kimi-K2.6 through recursive self-improvement — each round, a training agent plans a target capability, trains the model, evaluates benchmark trajectories, and refines the data mixture from observed failures, with humans gating every keep-or-revert decision — it handles the work healthcare models are actually asked to do: - Patient consultation: open-ended health conversations, graded hard by physician-written rubrics - Clinical reasoning over text and medical images: expert-exam-level diagnosis, treatment, and basic-science questions (text + vision, 256K context) - Interactive diagnosis and EHR tool use: multi-turn consultations and FHIR-based record operations, end to end
ResourcesPDF
ACTAVA | The AI Factory Architecture
Actava.ai is the only agentic lifecycle platform purpose-built for healthcare, enabling organizations to move agentic AI from pilot to production across enterprise operations without taking on more risks or unpredictable costs. It gives healthcare leaders control of the full lifecycle, safe orchestration across systems, and measurable ROI from day one, so every agent is specialized, auditable, and built to scale.
ResourcesPDF
ACTAVA | The AI Factory for Providers
A short look at how ACTAVA lets provider organizations build their own agents, with business and technical teams working the same process. For operators tired of waiting on an engineering queue to automate the work that's eating their margins.
ResourcesPDF
ACTAVA | The AI Factory for Consultants
Consulting's pyramid model is flattening into a diamond as agents absorb the junior-level work. This ACTAVA resource covers how consultants extend senior capacity, keep judgment and relationships human, and sell agent-building to clients now growing their own inference budgets.
ResourcesPDF
ACTAVA | The AI Factory for Human Resources
A look at how ACTAVA standardizes the way People Operations teams build, train, test, and deploy AI agents. Useful if your HR queue is mostly the same questions in different words, and hiring more coordinators hasn't changed that.
ResourcesPDF
ACTAVA | The AI Factory for Sales & Marketing
Sales and marketing AI usually shows up as scattered one-offs that nobody can reuse. This resource lays out how ACTAVA standardizes the creation, training, and deployment of agents so each new one starts from the work already done.
See what ACTAVA can do for you
Bring one workflow your team still runs by hand. We'll show you the agent that runs it.