Player-Driven Emergence in LLM-Driven Game Narrative
Open accessAbstract
We explore how interaction with large language models (LLMs) can give rise to emergent behaviors, empowering players to participate in the evolution of game narratives. Our testbed is a text-adventure game in which players attempt to solve a mystery under a fixed narrative premise, but can freely interact with non-player characters generated by GPT-4, a large language model. We recruit 28 gamers to play the game and use GPT-4 to automatically convert the game logs into a node-graph representing the narrative in the player’s gameplay. We find that through their interactions with the non-deterministic behavior of the LLM, players are able to discover interesting new emergent nodes that were not a part of the original narrative but have potential for being fun and engaging. Players that created the most emergent nodes tended to be those that often enjoy games that facilitate discovery, exploration and experimentation.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Interactions with LLMs can lead to emergent storytelling opportunities, enhancing player engagement and creativity.
“Prior work showed that interactions with LLMs can lead to emergent storytelling opportunities, enhancing player engagement and creativity (Peng et al., 2024).”
From Game Plot Design With an LLM-Powered Assistant: An Empirical Study With Game Designers (2026) · cites this paper as Peng et al., 2024
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Voyager: An Open-Ended Embodied Agent with Large Language Models
Wang, G., Xie, Y., Jiang, Y., Mandlekar, A., Xiao, C., Zhu, Y., Fan, L., & Anandkumar, A. (2023) · arXiv · doi:10.48550/arxiv.2305.16291 · Cited by 222 · cited 1× · see citing works
“[24] introduce an LLM-driven learning agent in Minecraft that continually explores the world, acquires skills, and makes discoveries without human intervention.”
BackgroundCreative Writing with an AI-Powered Writing Assistant: Perspectives from Professional Writers
Ippolito, D., Yuan, A., Coenen, A., & Burnam, S. (2022) · arXiv · doi:10.48550/arxiv.2211.05030 · Cited by 52 · see citing works
Volum, R., Rao, S., Xu, M., DesGarennes, G., Brockett, C., Van Durme, B., Deng, O., Malhotra, A., & Dolan, B. (2022) · Proceedings of the 3rd Wordplay: When Language Meets Games Workshop (Wordplay 2022) · doi:10.18653/v1/2022.wordplay-1.3 · Cited by 30 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 27
- J. van Stegeren and J. Myśliwiec, "Fine-tuning gpt-2 on annotated rpg quests for npc dialogue generation," in Proceedings of the 16th International Conference on the Foundations of Digital Games, 2021, pp. 1-8.
- S. Värtinen, P. Hämäläinen, and C. Guckelsberger, "Generating role- playing game quests with gpt language models," IEEE Transactions on Games, 2022.
- Q. C. Gao and A. Emami, "The turing quest: Can transformers make good npcs?" in Proceedings of the 61st Annual Meeting of the As- sociation for Computational Linguistics (Volume 4: Student Research Workshop), 2023, pp. 93-103.
- V. Kumaran, J. Rowe, B. Mott, and J. Lester, "Scenecraft: automating interactive narrative scene generation in digital games with large lan- guage models," in Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, vol. 19, no. 1, 2023, pp. 86-96.
- M. O. Riedl and A. Zook, "Ai for game production," in 2013 IEEE Conference on Computational Inteligence in Games (CIG), 2013, pp. 1-8.
- L. Huang and X. Sun, "Create ice cream: Real-time creative element synthesis framework based on gpt3.0," in 2023 IEEE Conference on Games (CoG), 2023, pp. 1-4.
- J. Murray, Hamlet on the Holodeck: The Future of Narrative in Cyberspace. Free Press, 1997. [Online]. Available: https: //books.google.co.jp/books?id=bzmSLtnMZJsC
- S. Chauvin, G. Levieux, J.-Y. Donnart, and S. Natkin, "Making sense of emergent narratives: An architecture supporting player-triggered narra- tive processes," in 2015 IEEE Conference on Computational Intelligence and Games (CIG), 2015, pp. 91-98.
- G. Franceschelli and M. Musolesi, "On the creativity of large language models," arXiv preprint arXiv:2304.00008, 2023. · arXiv
- M.-A. Côté, A. Kádár, X. Yuan, B. Kybartas, T. Barnes, E. Fine, J. Moore, M. Hausknecht, L. El Asri, M. Adada et al., "Textworld: A learning environment for text-based games," in Computer Games: 7th Workshop, CGW 2018, Held in Conjunction with the 27th International Conference on Artificial Intelligence, IJCAI 2018, Stockholm, Sweden, July 13, 2018, Revised Selected Papers 7. Springer, 2019, pp. 41-75.
- OpenAI, "Gpt-4 technical report," ArXiv, vol. abs/2303.08774, 2023. [Online]. Available: https://api.semanticscholar.org/CorpusID: 257532815 · arXiv
- F. P. Miller, A. F. Vandome, and J. McBrewster, Interactive Fiction: Computer Software, Command (Computing), Player Character, Nar- rative, Video Game, Adventure Game, Video Game Genres, Puzzle, Graphic Adventure Game. Alpha Press, 2009.
- J. Urbanek, A. Fan, S. Karamcheti, S. Jain, S. Humeau, E. Dinan, T. Rocktäschel, D. Kiela, A. Szlam, and J. Weston, "Learning to speak and act in a fantasy text adventure game," in Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019, pp. 673-683.
- M. Hausknecht, P. Ammanabrolu, M.-A. Côté, and X. Yuan, "Interactive fiction games: A colossal adventure," in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 05, 2020, pp. 7903- 7910.
- S. Yao, R. Rao, M. Hausknecht, and K. Narasimhan, "Keep CALM and explore: Language models for action generation in text-based games," in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), B. Webber, T. Cohn, Y. He, and Y. Liu, Eds. Online: Association for Computational Linguistics, Nov. 2020, pp. 8736-8754. [Online]. Available: https://aclanthology.org/2020.emnlp-main.704
- Y. Xu, M. Fang, L. Chen, Y. Du, and C. Zhang, "Generalization in text-based games via hierarchical reinforcement learning," in Findings of the Association for Computational Linguistics: EMNLP 2021, 2021, pp. 1343-1353.
- Y. Xu, M. Fang, L. Chen, Y. Du, J. Zhou, and C. Zhang, "Perceiving the world: Question-guided reinforcement learning for text-based games," in Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022, pp. 538-560.
- W. Zhou, X. Peng, and M. Riedl, "Dialogue shaping: Empowering agents through npc interaction," arXiv preprint arXiv:2307.15833, 2023. · arXiv
- C. F. Tsai, X. Zhou, S. S. Liu, J. Li, M. Yu, and H. Mei, "Can large language models play text games well? current state-of-the-art and open questions," arXiv preprint arXiv:2304.02868, 2023. · arXiv
- S. Basavatia, S. Ratnakar, and K. Murugesan, "Complexworld: A large language model-based interactive fiction learning environment for text- based reinforcement learning agents," in International Joint Conference on Artificial Intelligence, 2023.
- A. Kalbiyev, "Affective dialogue generation for video games," Master's thesis, University of Twente, 2022.
- M. U. Nasir and J. Togelius, "Practical pcg through large language models," arXiv preprint arXiv:2305.18243, 2023. · arXiv
- G. Todd, S. Earle, M. U. Nasir, M. C. Green, and J. Togelius, "Level generation through large language models," in Proceedings of the 18th International Conference on the Foundations of Digital Games, 2023, pp. 1-8.
- S. Värtinen, P. Hämäläinen, and C. Guckelsberger, "Generating role- playing game quests with gpt language models," IEEE Transactions on Games, pp. 1-12, 2022.
- K. Frans, "Ai charades: Language models as interactive game environ- ments," in 2021 IEEE Conference on Games (CoG), 2021, pp. 1-2.
- Y. Xu, S. Wang, P. Li, F. Luo, X. Wang, W. Liu, and Y. Liu, "Exploring large language models for communication games: An empirical study on werewolf," arXiv preprint arXiv:2309.04658, 2023. · arXiv
- E. Akata, L. Schulz, J. Coda-Forno, S. J. Oh, M. Bethge, and E. Schulz, "Playing repeated games with large language models," arXiv preprint arXiv:2305.16867, 2023. · arXiv
Cited by
Sorted by citations
Game Plot Design With an LLM-Powered Assistant: An Empirical Study With Game Designers
Alavi, S. H., Xu, W., Jojic, N., Kennett, D., Ng, R. T., Rao, S., Zhang, H., Dolan, B., & Shwartz, V. (2026) · IEEE Transactions on Games · doi:10.1109/tg.2026.3663566
Self-citation
- Authors
- Peng, X., Quaye, J., Rao, S., Xu, W., Botchway, P., Brockett, C., Jojic, N., DesGarennes, G., Lobb, K., Xu, M., Leandro, J., Jin, C., & Dolan, B.
- Affiliations
- Microsoft (United States) (US)
- Microsoft Research
- Venue
- 2024 IEEE Conference on Games (CoG)
- Publisher
- IEEE
- Published
- 2024-08-05
- Pages
- 1-8
- OpenAlex
- W4401943744
- Cited by
- 27
- References
- 3
- Citations by year
- 2026: 12 · 2025: 14 · 2024: 1
- FWCI
- 7.80
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Conference on Games (CoG) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence in Games
- Social Sciences › Sociology and Political Science › Digital Games and Media
- Social Sciences › Psychology › Developmental and Educational Psychology › Educational Games and Gamification
- Keywords
- large language models, game narrative, emergent behavior, text adventure games, GPT-4, non-player characters, player engagement
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
