Gemini Robotics Team: multimodal embodied reasoning and action

What changed

Adapted a multimodal foundation model into embodied-reasoning and vision-language-action models, reporting manipulation generalization and few-shot specialization across tasks and embodiments.

Scientific scope

Adapted a multimodal foundation model into embodied-reasoning and vision-language-action models, reporting manipulation generalization and few-shot specialization across tasks and embodiments. The Robotics and Robotics-ER reports form one family contribution. Few-shot and new-embodiment claims require the stated training/fine-tuning; they are not universal zero-shot robotics or a safety certification.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. The Robotics and Robotics-ER reports form one family contribution. Few-shot and new-embodiment claims require the stated training/fine-tuning; they are not universal zero-shot robotics or a safety certification.

Contributors

• Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.

• Gemini Robotics: Bringing AI into the Physical World
• Gemini Robotics Team: multimodal embodied reasoning and action — official research record

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction