# Human-level play in the game of Diplomacy by combining language models with strategic reasoning

*Source* · `src-fair-2022-cicero` · status: **n/a**

| field | value |
|---|---|
| kind | Peer-reviewed paper |
| authors | Meta Fundamental AI Research Diplomacy Team (FAIR) |
| venue | Science 378(6624):1067-1074 |
| date | 2022-11-22 |
| doi | 10.1126/science.ade9097 |
| accessed | 2026-10-24 |

## Notes

Cicero: language model plus planning and RL; in 40 games of an anonymous online league it scored more than double the human average and ranked in the top 10% of participants who played more than one game.

## Backlinks (computed)

**cited by:** [Language models grounded in strategic planning for negotiation games](../technique/cicero-strategic-dialogue.md)

## Citation

Meta Fundamental AI Research Diplomacy Team (FAIR) (2022-11-22). *Human-level play in the game of Diplomacy by combining language models with strategic reasoning*. Science 378(6624):1067-1074 https://doi.org/10.1126/science.ade9097

---
Provenance: created in run `2026-10-24-techniques-rl-design`.