SIMA Team: language-instructable agents across simulated worlds

What changed

Trained agents on natural-language instructions and visual observations across diverse 3D environments, acting through keyboard-and-mouse interfaces rather than privileged game state.

Scientific scope

Trained agents on natural-language instructions and visual observations across diverse 3D environments, acting through keyboard-and-mouse interfaces rather than privileged game state. Preliminary finite-game results do not fulfill the stated goal of arbitrary instructions in any world. A shared interface and cross-game experiments do not establish general intelligence or real-robot transfer.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Preliminary finite-game results do not fulfill the stated goal of arbitrary instructions in any world. A shared interface and cross-game experiments do not establish general intelligence or real-robot transfer.

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.

• Scaling Instructable Agents Across Many Simulated Worlds
• SIMA Team: language-instructable agents across simulated worlds — 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