{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T23:18:12Z","timestamp":1761175092718,"version":"build-2065373602"},"reference-count":28,"publisher":"Polish Information Processing Society","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.15439\/2025f1909","type":"proceedings-article","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T07:44:23Z","timestamp":1761119063000},"page":"739-745","source":"Crossref","is-referenced-by-count":0,"title":["Towards Game Level Generation Through LLM and GAN"],"prefix":"10.15439","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1347-4377","authenticated-orcid":true,"given":"Filip","family":"Martinovi\u0107","sequence":"first","affiliation":[{"name":"University of Zagreb, Faculty of Electrical Engineering and Computing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5248-7223","authenticated-orcid":true,"given":"Danijel","family":"Mlinari\u0107","sequence":"additional","affiliation":[{"name":"University of Zagreb, Faculty of Electrical Engineering and Computing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5221-6848","authenticated-orcid":true,"given":"Juraj","family":"Don\u010devi\u0107","sequence":"additional","affiliation":[{"name":"University of Zagreb, Faculty of Electrical Engineering and Computing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8304-5463","authenticated-orcid":true,"given":"Agneza","family":"Krajna","sequence":"additional","affiliation":[{"name":"University of Zagreb, Faculty of Electrical Engineering and Computing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7378-3339","authenticated-orcid":true,"given":"Ivica","family":"Boti\u010dki","sequence":"additional","affiliation":[{"name":"University of Zagreb, Faculty of Electrical Engineering and Computing"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"6175","published-online":{"date-parts":[[2025,10,15]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","unstructured":"G. N. Yannakakis and J. Togelius, \u2018Experience-Driven Procedural Content Generation\u2019, IEEE Trans. Affect. Comput., vol. 2, no. 3, pp. 147\u2013161, Jul. 2011, https:\/\/dx.doi.org\/10.1109\/T-AFFC.2011.6.","DOI":"10.1109\/T-AFFC.2011.6"},{"key":"ref2","unstructured":"D. Mlinari\u0107, \u2018Extension of dynamic software update model for class hierarchy changes and run-time phenomena detection\u2019, info:eu-repo\/semantics\/doctoralThesis, University of Zagreb. Faculty of Electrical Engineering and Computing. Department of Applied Computing, 2020. Accessed: May 26, 2025. [Online]. Available: https:\/\/urn.nsk.hr\/urn:nbn:hr:168:087042"},{"key":"ref3","doi-asserted-by":"publisher","unstructured":"D. Mlinari\u0107, J. Don\u010devi\u0107, M. Br\u010di\u0107, and I. Boti\u010dki, \u2018Revolutionizing Software Development: Autonomous Software Evolution\u2019, in 2024 47th MIPRO ICT and Electronics Convention (MIPRO), May 2024, pp. 224\u2013228. https:\/\/dx.doi.org\/10.1109\/MIPRO60963.2024.10569871.","DOI":"10.1109\/MIPRO60963.2024.10569871"},{"key":"ref4","doi-asserted-by":"publisher","unstructured":"N. Shaker, J. Togelius, and M. J. Nelson, Procedural Content Generation in Games. in Computational Synthesis and Creative Systems. Cham: Springer International Publishing, 2016. https:\/\/dx.doi.org\/10.1007\/978-3-319-42716-4.","DOI":"10.1007\/978-3-319-42716-4"},{"key":"ref5","doi-asserted-by":"publisher","unstructured":"J. Togelius, E. Kastbjerg, D. Schedl, and G. N. Yannakakis, \u2018What is procedural content generation? Mario on the borderline\u2019, in Proceedings of the 2nd International Workshop on Procedural Content Generation in Games, in PCGames \u201911. New York, NY, USA: Association for Computing Machinery, Jun. 2011, pp. 1\u20136. https:\/\/dx.doi.org\/10.1145\/2000919.2000922.","DOI":"10.1145\/2000919.2000922"},{"key":"ref6","doi-asserted-by":"publisher","unstructured":"I. J. Goodfellow et al., \u2018Generative Adversarial Networks\u2019, Jun. 10, 2014, https:\/\/arxiv.org\/abs\/ arXiv:1406.2661. https:\/\/dx.doi.org\/10.48550\/arXiv.1406.2661.","DOI":"10.48550\/arXiv.1406.2661"},{"key":"ref7","doi-asserted-by":"publisher","unstructured":"A. Vaswani et al., \u2018Attention Is All You Need\u2019, Jun. 12, 2017, https:\/\/arxiv.org\/abs\/ arXiv:1706.03762. https:\/\/dx.doi.org\/10.48550\/arXiv.1706.03762.","DOI":"10.48550\/arXiv.1706.03762"},{"key":"ref8","doi-asserted-by":"publisher","unstructured":"A. Dosovitskiy et al., \u2018An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale\u2019, Oct. 22, 2020, https:\/\/arxiv.org\/abs\/ arXiv:2010.11929. https:\/\/dx.doi.org\/10.48550\/arXiv.2010.11929.","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref9","doi-asserted-by":"publisher","unstructured":"A. Summerville et al., \u2018Procedural Content Generation via Machine Learning (PCGML)\u2019, IEEE Trans. Games, vol. 10, no. 3, pp. 257\u2013270, Sep. 2018, https:\/\/dx.doi.org\/10.1109\/TG.2018.2846639.","DOI":"10.1109\/TG.2018.2846639"},{"key":"ref10","doi-asserted-by":"publisher","unstructured":"V. Volz, J. Schrum, J. Liu, S. M. Lucas, A. Smith, and S. Risi, \u2018Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Network\u2019, May 02, 2018, https:\/\/arxiv.org\/abs\/ arXiv:1805.00728. https:\/\/dx.doi.org\/10.48550\/arXiv.1805.00728.","DOI":"10.48550\/arXiv.1805.00728"},{"key":"ref11","doi-asserted-by":"publisher","unstructured":"N. Hansen, S. D. M\u00fcller, and P. Koumoutsakos, \u2018Reducing the Time Complexity of the Derandomized Evolution Strategy with Covariance Matrix Adaptation (CMA-ES)\u2019, Evol. Comput., vol. 11, no. 1, pp. 1\u201318, Mar. 2003, https:\/\/dx.doi.org\/10.1162\/106365603321828970.","DOI":"10.1162\/106365603321828970"},{"key":"ref12","doi-asserted-by":"publisher","unstructured":"R. Rodriguez Torrado, A. Khalifa, M. Cerny Green, N. Justesen, S. Risi, and J. Togelius, \u2018Bootstrapping Conditional GANs for Video Game Level Generation\u2019, in 2020 IEEE Conference on Games (CoG), Aug. 2020, pp. 41\u201348. https:\/\/dx.doi.org\/10.1109\/CoG47356.2020.9231576.","DOI":"10.1109\/CoG47356.2020.9231576"},{"key":"ref13","doi-asserted-by":"publisher","unstructured":"M. Bazzaz and S. Cooper, \u2018Guided Game Level Repair via Explainable AI\u2019, Nov. 04, 2024, https:\/\/arxiv.org\/abs\/ arXiv:2410.23101. https:\/\/dx.doi.org\/10.48550\/arXiv.2410.23101.","DOI":"10.48550\/arXiv.2410.23101"},{"key":"ref14","unstructured":"S. M. Lundberg and S.-I. Lee, \u2018A Unified Approach to Interpreting Model Predictions\u2019, in Advances in Neural Information Processing Systems, Curran Associates, Inc., 2017. Accessed: Apr. 02, 2025. [Online]. Available: https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/hash\/8a20a8621978632d76c43dfd28b67767-Abstract.html"},{"key":"ref15","doi-asserted-by":"publisher","unstructured":"N. Kokhlikyan et al., \u2018Captum: A unified and generic model interpretability library for PyTorch\u2019, Sep. 16, 2020, https:\/\/arxiv.org\/abs\/ arXiv:2009.07896. https:\/\/dx.doi.org\/10.48550\/arXiv.2009.07896.","DOI":"10.48550\/arXiv.2009.07896"},{"key":"ref16","doi-asserted-by":"publisher","unstructured":"H. Zhang, M. C. Fontaine, A. K. Hoover, J. Togelius, B. Dilkina, and S. Nikolaidis, \u2018Video Game Level Repair via Mixed Integer Linear Programming\u2019, Oct. 13, 2020, https:\/\/arxiv.org\/abs\/ arXiv:2010.06627. https:\/\/dx.doi.org\/10.48550\/arXiv.2010.06627.","DOI":"10.48550\/arXiv.2010.06627"},{"key":"ref17","unstructured":"S. Cooper and A. Sarkar, \u2018Pathfinding Agents for Platformer Level Repair\u2019."},{"key":"ref18","unstructured":"R. Jain, A. Isaksen, and C. Holmg, \u2018Autoencoders for Level Generation, Repair, and Recognition\u2019."},{"key":"ref19","doi-asserted-by":"publisher","unstructured":"G. E. Hinton and R. R. Salakhutdinov, \u2018Reducing the Dimensionality of Data with Neural Networks\u2019, Science, vol. 313, no. 5786, pp. 504\u2013507, Jul. 2006, https:\/\/dx.doi.org\/10.1126\/science.1127647.","DOI":"10.1126\/science.1127647"},{"key":"ref20","unstructured":"\u2018Google Snake Mods\u2019. Accessed: Apr. 04, 2025. [Online]. Available: https:\/\/googlesnakemods.com\/v\/4\/"},{"key":"ref21","unstructured":"\u2018DarkSnakeGang\/GoogleSnakeLevelEditor: Level Editor Mod for Google Snake\u2019. Accessed: Apr. 08, 2025. [Online]. Available: https:\/\/github.com\/DarkSnakeGang\/GoogleSnakeLevelEditor"},{"key":"ref22","doi-asserted-by":"publisher","unstructured":"A. J. Summerville, S. Snodgrass, M. Mateas, and S. Onta\u00f1\u00f3n, \u2018The VGLC: The Video Game Level Corpus\u2019, Jul. 03, 2016, https:\/\/arxiv.org\/abs\/ arXiv:1606.07487. https:\/\/dx.doi.org\/10.48550\/arXiv.1606.07487.","DOI":"10.48550\/arXiv.1606.07487"},{"key":"ref23","doi-asserted-by":"publisher","unstructured":"M. Arjovsky, S. Chintala, and L. Bottou, \u2018Wasserstein GAN\u2019, Dec. 06, 2017, https:\/\/arxiv.org\/abs\/ arXiv:1701.07875. https:\/\/dx.doi.org\/10.48550\/arXiv.1701.07875.","DOI":"10.48550\/arXiv.1701.07875"},{"key":"ref24","doi-asserted-by":"publisher","unstructured":"C. Little, M. Elliot, R. Allmendinger, and S. S. Samani, \u2018Generative Adversarial Networks for Synthetic Data Generation: A Comparative Study\u2019, Dec. 03, 2021, https:\/\/arxiv.org\/abs\/ arXiv:2112.01925. https:\/\/dx.doi.org\/10.48550\/arXiv.2112.01925.","DOI":"10.48550\/arXiv.2112.01925"},{"key":"ref25","unstructured":"\u2018Structured Outputs - OpenAI API\u2019. Accessed: May 24, 2025. [Online]. Available: https:\/\/platform.openai.com"},{"key":"ref26","unstructured":"\u2018LangChain\u2019. Accessed: May 22, 2025. [Online]. Available: https:\/\/www.langchain.com\/langchain"},{"key":"ref27","doi-asserted-by":"publisher","unstructured":"P. E. Hart, N. J. Nilsson, and B. Raphael, \u2018A Formal Basis for the Heuristic Determination of Minimum Cost Paths\u2019, IEEE Trans. Syst. Sci. Cybern., vol. 4, no. 2, pp. 100\u2013107, Jul. 1968, https:\/\/dx.doi.org\/10.1109\/TSSC.1968.300136.","DOI":"10.1109\/TSSC.1968.300136"},{"key":"ref28","unstructured":"\u2018Optuna - A hyperparameter optimization framework\u2019, Optuna. Accessed: May 23, 2025. [Online]. Available: https:\/\/optuna.org\/"}],"event":{"name":"20th Conference on Computer Science and Intelligence Systems (FedCSIS)","theme":"Computer Science and Intelligence Systems","location":"Krak\u00f3w, Poland","acronym":"FedCSIS","number":"20","start":{"date-parts":[[2025,9,14]]},"end":{"date-parts":[[2025,9,17]]}},"container-title":["Annals of Computer Science and Information Systems","Proceedings of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS)"],"original-title":[],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T07:51:22Z","timestamp":1761119482000},"score":1,"resource":{"primary":{"URL":"https:\/\/annals-csis.org\/Volume_43\/drp\/1909.html"}},"subtitle":[],"proceedings-subject":"Computer Science and Information Systems","short-title":[],"issued":{"date-parts":[[2025,10,15]]},"references-count":28,"URL":"https:\/\/doi.org\/10.15439\/2025f1909","relation":{},"ISSN":["2300-5963"],"issn-type":[{"value":"2300-5963","type":"print"}],"subject":[],"published":{"date-parts":[[2025,10,15]]}}}