The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Towards Authoring Open-Ended Behaviors for Narrative Puzzle Games with Large Language Model Support
Abstract
Designing games with branching story lines, object annotations, scene details, and dialog can be challenging due to the intensive authoring required. We investigate the potential for authoring open-ended behaviors for point-and-click narrative games using GPT-3.5, a large language model. In our approach, we extend a behavior tree scripting system with nodes that query GPT-3.5 to generate object descriptions, conversations with characters, and responses to player actions. GPT-3.5 is used to generate content when it hasn’t been scripted manually and to update game state by asking questions about whether a player’s input achieves a particular game goal. We demonstrate our approach with puzzles based on scenes from an episode of Star Trek Voyager. Our approach aims to blend a specific plot with open-ended story elements while keeping the authoring work minimal. Based on a pilot study of 16 participants and our own testing, we find that the generated responses have high coherency and show signs of humor and novelty, but that utterances could be improved to be more interesting and better support the designer’s intent.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Training language models to follow instructions with human feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.02155 · Cited by 4,208
Training Language Models to Follow Instructions with Human Feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-2011 · Cited by 3,117
GPTScore: Evaluate as You Desire
Fu, J., Ng, S.-K., Jiang, Z., & Liu, P. (2023) · arXiv · doi:10.48550/arxiv.2302.04166 · Cited by 446
Large Language Models and Games: A Survey and Roadmap
Gallotta, R., Todd, G., Zammit, M., Earle, S., Liapis, A., Togelius, J., & Yannakakis, G. N. (2024) · IEEE Transactions on Games · doi:10.1109/tg.2024.3461510 · Cited by 137
Say Anything: Using Textual Case-Based Reasoning to Enable Open-Domain Interactive Storytelling
Swanson, R., & Gordon, A. S. (2012) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/2362394.2362398 · Cited by 85 · cited 1×
“Similarly, Dart et al. [1] used a database to create variety in puzzles and Swanson and Gordon’s Say Anything [10] used a corpus of blogs to co-create stories between a player and the system.”
Kumaran, V., Rowe, J., Mott, B., & Lester, J. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · doi:10.1609/aiide.v19i1.27504 · Cited by 78
Integrated taxonomy of errors in chat-oriented dialogue systems
Higashinaka, R., Araki, M., Tsukahara, H., & Mizukami, M. (2021) · Annual Meeting of the Special Interest Group on Discourse and Dialogue · doi:10.18653/v1/2021.sigdial-1.10 · Cited by 46
Procedural Generation of Narrative Puzzles in Adventure Games
Fernández-Vara, C., & Thomson, A. (2012) · doi:10.1145/2538528.2538538 · Cited by 31
Smart terrain causality chains for adventure-game puzzle generation
Dart, I. M., & Nelson, M. (2012) · IEEE Conference on Computational Intelligence and Games (CIG) · doi:10.1109/cig.2012.6374173 · Cited by 12
An Ontology of Co-Creative AI SystemsPreprint
Lin, Z., & Riedl, M. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.07472 · Cited by 4
Research works printed but not linked: 2
- Joon Sung Park, Joseph C O’Brien, Carrie J Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. arXiv preprint arXiv:2304.03442 (2023). · arXiv
- Mike Wollaeger, Jessica Scott, Bryan Fuller, and Michael Taylor. 1999. Star Trek: Voyager Episode 608: One Small Step. http://www.chakoteya.net/Voyager/607.htm Accessed July 2023.
Cited by
GPT for Games: An Updated Scoping Review (2020–2024)
Yang, D., Kleinman, E., & Harteveld, C. (2025) · IEEE Transactions on Games · doi:10.1109/tg.2025.3563780 · Cited by 50
“GPT for character generation (n = 18, [43], [72], [73], [74], [75], [76], [77], [78], [79], [80], [81], [82], [83], [84], [85], [86], [87], [88]): In 2024, the use of GPT to generate in-game characters has attracted significant research attention ( n = 15 ).”
Orchid: A Creative Approach for Authoring LLM-Driven Interactive Narratives
Wu, Z., Kumyol, S., Wong, S., Hu, X., Tong, X., & Braud, T. (2025) · Creativity and Cognition · doi:10.1145/3698061.3726906 · Cited by 14
“This is addressed in works including using LLMs in making plans for the event [55], guiding NPCs’ dialogues without human intervention [4, 6, 13, 38, 46, 53, 75, 82], and generating game levels governing complex functional constraints and spatial relationships [8, 34, 45, 74].”
The Curation Tree: A Lightweight Behavior Tree Framework for Implementing Puzzle and Narrative Games
Normoyle, A., Jörg, S., & Hill, J. (2024) · International Conference on the Foundations of Digital Games (FDG) · doi:10.1145/3649921.3659840 · Cited by 3
“We are using this system to develop games for testing conversational agents [10, 11] (Figure 6).”
MethodSelf-citationOrchid-Creator: An Authoring Tool Supporting LLM-Driven Interactive Narrative Creation
Wu, Z., Kumyol, S., Ma, Z., & Braud, T. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791426 · Cited by 2
“NPC dialogue generation using LLMs creates dynamic player interactions, as seen in works by Sun et al. with social chatbots [47], and Kumaran et al. with branching dialogues [30], and Ngaw et al. for character and object descriptions [37].”
InkStack: A Programmable E-Paper Card System for Board Games
Dominiak, J., Walczak, A., Sałata, A. J., Loerakker, M. B., Saigg, C. D. L., Romanowski, A., Grudzień, K., & Woźniak, P. W. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791715
Metadata
- Authors
- Ngaw, B., Jena, G., Sedoc, J., & Normoyle, A.
- Affiliations
- New York University (US)
- IBM (United States) (US)
- Bryn Mawr College (US)
- Venue
- Proceedings of the 19th International Conference on the Foundations of Digital Games
- Publisher
- ACM
- Published
- 2024-05-21
- Pages
- 1-4
- OpenAlex
- W4400361227
- Cited by
- 5
- References
- 9
- Citations by year
- 2026: 2 · 2025: 2 · 2024: 1
- FWCI
- 1.44
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on the Foundations of Digital Games (FDG) (publishedVersion)
- 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
- point-and-click games, game authoring, large language models, GPT-3.5, behavior trees, Star Trek: Voyager, branching narratives, game design automation
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Towards Authoring Open-Ended Behaviors for Narrative Puzzle Games with Large Language Model Support. https://app.cochat.ai/papers/10.1145/3649921.3656975
- The paper
- Ngaw, B., Jena, G., Sedoc, J., & Normoyle, A. (2024). Towards Authoring Open-Ended Behaviors for Narrative Puzzle Games with Large Language Model Support. Proceedings of the 19th International Conference on the Foundations of Digital Games. https://doi.org/10.1145/3649921.3656975
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.