# Player-Driven Emergence in LLM-Driven Game Narrative

*Source* · `src-peng-2024-player-driven-emergence` · status: **n/a**

| field | value |
|---|---|
| kind | Preprint |
| authors | Xiangyu Peng, Jessica Quaye, Sudha Rao, Weijia Xu, et al., Bill Dolan |
| venue | arXiv |
| date | 2024-04-25 |
| url | https://arxiv.org/abs/2404.17027 |
| arxiv | 2404.17027 |
| accessed | 2026-10-24 |

## Notes

Dejaboom! TextWorld mystery with five GPT-4 NPCs holding backstories, clues, and ordered goals; 28 players; GPT-4 turned logs into narrative graphs; 53 emergent nodes (43 unique) vs designer graph. About 15 s lag frustrated 40%; NPC forgetting 10%; repetition 10%.

## Backlinks (computed)

**cited by:** [LLM explanation of simulation state](../technique/llm-explanation-of-state.md), [LLM game master and narrative director](../technique/llm-game-master.md)

## Citation

Xiangyu Peng, Jessica Quaye, Sudha Rao, Weijia Xu, et al., Bill Dolan (2024-04-25). *Player-Driven Emergence in LLM-Driven Game Narrative*. arXiv https://arxiv.org/abs/2404.17027

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