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 storyResearch
29 articles
Research2 min read
Evaluating tool-integrated agents with MCPEval
An MCP-based framework connects automated task generation, verification, and trajectory analysis across several domains.
Research1 min read
How APIGen-MT constructs a multi-turn training conversation
A two-stage synthesis pipeline connects executable task plans with simulated agent–user interactions.
Research1 min read
ActionStudio and the data pipeline behind action-model training
A unified trajectory format, data verification, and distributed training support heterogeneous agent datasets.
Research1 min read
Personal context becomes an evaluation task in PersonaBench
Synthetic profiles and personal documents create a controlled setting for personalized retrieval and question answering.
Research2 min read
Seven tool-use error patterns made inspectable with ToolScan
A diagnostic benchmark organizes tool-calling failures by the function, arguments, format, and action sequence involved.
Research1 min read
LaTRO learns a distribution over reasoning paths
A variational training objective connects sampled reasoning with the model’s own answer-likelihood estimates.
Research1 min read
The training system behind the xLAM action-model family
A shared data pipeline unifies and synthesizes agent interactions across dense and mixture-of-experts models.
Research1 min read
Combining complementary coding agents with DEI
A committee reviews candidate fixes produced by different software-engineering agents and selects a patch for a repository issue.
Research1 min read
APIGen builds function-calling data through execution
Format checks, executable APIs, and semantic review give synthetic tool-use examples a structured verification process.
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.