Provides scientific-reasoning and tool-use trajectories for training agent foundation models, alongside reinforcement-learning tasks. Its staged data makes the Axion 1.0 training process easier to inspect and reproduce.
Turns a robot calibration episode and data request into synchronized, action-labelled training data: an agent builds the simulated task, while a video model renders realistic observations. Across five robot tasks, farm-trained policies scored 87 successes under unseen appearances, versus 46 for teleoperation-trained policies.
Builds tool-composition environments from real execution traces and generates verifiable long-horizon agent tasks. Results show substantial gains in models’ ability to coordinate tools across environments.
Evaluates AI agents on 56 research-based physics tasks, from literature review and experimentation to manuscript writing. It combines deterministic checks with expert rubrics to assess both correctness and research quality.
Turns plain-language prompts into working websites, web apps, and mobile apps in the browser. Chat-driven code generation, live preview, hosting, databases, and GitHub/Figma imports help builders move from idea to shipped project without local setup.
Turns plain-language app ideas into working software inside a browser workspace, then lets users preview, debug, and deploy without leaving the platform.
Memory layer that lets AI agents remember users and context across sessions.