# Large Language Models and Games: A Survey and Roadmap

*Source* · `src-gallotta-2024-llms-games-survey` · status: **n/a**

| field | value |
|---|---|
| kind | Peer-reviewed paper |
| authors | Roberto Gallotta, Graham Todd, Marvin Zammit, Sam Earle, Antonios Liapis, Julian Togelius, Georgios N. Yannakakis |
| venue | IEEE Transactions on Games |
| date | 2024 |
| url | https://arxiv.org/abs/2402.18659 |
| doi | 10.1109/TG.2024.3461510 |
| arxiv | 2402.18659 |
| accessed | 2026-10-24 |

## Notes

Nine roles: player, NPC, player assistant, commentator/reteller, analyst, game master, game mechanic, automated designer, design assistant. LLM GMs accommodate bizarre requests; NPCs may hallucinate quests; design-tool latency 30 s to over a minute; commentary and retelling research limited.

## Backlinks (computed)

**cited by:** [Generative agents (memory stream, reflection, planning)](../technique/generative-agents.md), [LLM explanation of simulation state](../technique/llm-explanation-of-state.md), [LLM game master and narrative director](../technique/llm-game-master.md)

## Citation

Roberto Gallotta, Graham Todd, Marvin Zammit, Sam Earle, Antonios Liapis, Julian Togelius, Georgios N. Yannakakis (2024). *Large Language Models and Games: A Survey and Roadmap*. IEEE Transactions on Games https://arxiv.org/abs/2402.18659

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