# Scaling Instructable Agents Across Many Simulated Worlds

*Source* · `src-deepmind-2024-sima-paper` · status: **n/a**

| field | value |
|---|---|
| kind | Preprint |
| authors | SIMA Team (Google DeepMind) |
| venue | arXiv |
| date | 2024-03-13 |
| url | https://arxiv.org/abs/2404.10179 |
| arxiv | 2404.10179 |
| accessed | 2026-10-24 |

## Notes

Agents take image observations and language instructions and output keyboard and mouse actions through a generic human-like interface in real time, across research environments and commercial games.

## Backlinks (computed)

**cited by:** [Generalist instructable game agents (SIMA)](../technique/generalist-game-agents.md)

## Citation

SIMA Team (Google DeepMind) (2024-03-13). *Scaling Instructable Agents Across Many Simulated Worlds*. arXiv https://arxiv.org/abs/2404.10179

---
Provenance: created in run `2026-10-24-techniques-llm-agents`.