1. Titles of the Publications - Video Game Procedural Content Generation Through Software Transplantation. ICSE SEIP 2025. - Game Software Engineering: A Controlled Experiment Comparing Automated Content Generation Techniques. ESEM 2024 (Best Paper Award). ----------------------------------------------------------------------------------------------------------------------- 2. the name, complete physical mailing address, e-mail address, and phone number of EACH author of EACH paper(s); Mar Zamorano 1,2 - maria.lopez.20@ucl.ac.uk Daniel Blasco 2 - dblasco@usj.es África Domingo 2 - adomingp@usj.es Carlos Cetina 1,3 - cetina@upv.es Federica Sarro 1 - f.sarro@ucl.ac.uk 1. University College London, Gower Street, London, WC1E 6BT Tel: +44 (0) 20 7679 2000 2. Universidad San Jorge, Campus Universitario Villanueva de Gállego Autov. A-23 Zaragoza-Huesca, Km. 299 50830 Villanueva de Gállego – Zaragoza Tel: (+34) 976 060 100 3. Universitat Politècnica de València, Camino de Vera, s/n 46022 - Valencia Tel: (+34) 96 387 70 00 ----------------------------------------------------------------------------------------------------------------------- 3. Corresponding author Mar Zamorano maria.lopez.20@ucl.ac.uk ----------------------------------------------------------------------------------------------------------------------- 4. Abstract of the papers - Software transplantation generates new piece of software by reusing existing parts from a given piece of software (i.e., host) to enhance other parts of a same or different software (i.e., donor). In this paper, we argue that software transplantation can be used for automatically producing video game content. We propose the first search-based algorithm for procedural content transplantation and empirically evaluating it in an industrial case study in collaboration with the developers of the commercial video game Kromaia. Specifically, our proposed approach, dubbed IMHOTEP, enables developers to choose what video-game content to transplant and where, and automatically searches for an appropriate solution to integrate the organ into the host. Such a search is performed by using an evolutionary algorithm guided by a simulation-based fitness function, which is novel w.r.t previous transplantation work generally guided by test-suite compliance. We empirically evaluate the effectiveness of IMHOTEP to transplant procedural content, specifically non-playable characters, for the commercial video game Kromaia and benchmarked it against a state-of-the-art approach in search-based procedural content generation, as well as a variant of IMHOTEP itself guided by a test-suite-based fitness function. Using IMHOTEP, Kromaia developers were able to transplant 129 distinct organs taken from the game’s scenarios into five different hosts, thus generating a total of 645 new transplanted non-playable characters for this game. Moreover, we found that the game content generated by using IMHOTEP was 1.5 times superior to the one obtained by using its test-suite-based variant, and 2.5 times superior than the one generated by the state-of-the-art benchmark. Finally, a focus group with game developers indicated their satisfaction with the content generated by IMHOTEP and their willingness to use it for game development. - Background. Video games are complex projects that involve a seamless integration of art and software during the development process to compose the final product. In the creation of a video game, software is fundamental as it governs the behavior and attributes that shape the player’s experience within the game. When assessing the quality of a video game, one needs to consider specific quality aspects, namely ‘design’, ‘difficulty’, ‘fun’, and ‘immersiveness’, which are not considered for traditional software. On the other hand, there are not well-established best practices for the empirical assessment of video games as there are for the empirical evaluation of more traditional software. Aims. Our goal is to carry out a rigorous empirical evaluation of the latest proposals to automatically generate content for video games following best practices established in software engineering research. Specifically, we compare Procedural Content Generation (PCG) and Reuse-based Content Generation (RCG). Our study also considers the perception of players and professional developers on the generated content. Method. We conducted a controlled experiment where human subjects had to play with content that was automatically generated for a commercial video game by the two techniques (PCG and RCG), and evaluate it according to specific quality aspects of video games. A total of 44 subjects including professional developers and players participated in our experiment. Results. The results suggest that participants perceive that RCG generates content is of higher quality than PCG. Conclusions. The results can turn the tide for content generation. So far, RCG has been neglected as a viable option: typically, reuse is frowned upon by the developers, who aim to avoid repetition in their video games as much as possible. However, our study uncovered that RCG unlocks latent content that is actually favoured by players and developers alike. This revelation poses an opportunity towards opening new horizons for content generation research. ----------------------------------------------------------------------------------------------------------------------- 5. Criteria that the author claims that the work satisfies (B) The result is equal to or better than a result that was accepted as a new scientific result at the time when it was published in a peer-reviewed scientific journal. (D) The result is publishable in its own right as a new scientific result independent of the fact that the result was mechanically created. (E) The result is equal to or better than the most recent human-created solution to a long-standing problem for which there has been a succession of increasingly better human-created solutions. ----------------------------------------------------------------------------------------------------------------------- 6. Statement Why the Results Satisfy the Criteria Procedural content generation (PCG) has been a hot research topic with a progression of increasingly sophisticated human-designed and algorithmic solutions, which has witness over 300 peer-reviewed scientific articles in the past 10 years. Our work proposes IMHOTEP, the first search-based procedural content transplantation system that reuses existing software components to generate new video game content. Moreover, we evaluated the effectiveness of IMHOTEP in a real-world industrial setting with the commercial video game Kromaia. The results obtained show that our approach outperforms a state-of-the-art search-based PCG method and a test-suite-based variant of IMHOTEP by 2.5x and 1.5x respectively in terms of generated content quality. The evaluation of IMHOTEP includes a controlled experiment involving game developers and players, who assessed game content quality across several key dimensions such as fun, immersiveness, and design. The feedback indicates that a transplantation approach leads to content that is perceived as higher quality compared to PCG. These findings align with and go beyond results previously accepted in peer-reviewed literature in the fields of software engineering and game development, and are thus better than widely accepted scientific results previously published in a peer-reviewed scientific journal (B). Moreover in the controlled experiment, both developers and players judged the solutions created by IMHOTEP not only superior than state-of-the-art PCG but also human-competitive when compared to the game original content which was handcrafted by the developers, thus confirming that IMHOTEP's results are equal to or better than the most recent human-created solution (E). Our proposal IMHOTEP and its rigorous empirical evaluation in an industrial context with real-world developers and users has yield novel insights and relevant scientific contributions in a practical setting (the commercial video game Kromaia). The transplant algorithm guided by simulation-based fitness represents per se a fundamental advance in content generation methodologies, and the study of developer and player perception provides a new direction for evaluating game content. These results are independently publishable as new scientific findings in their own right independent of the fact that the result was mechanically created (D). In fact, IMHOTEP has been published in the top tier software engineering conference ICSE, while the empirical user-study has been published in the premier venue for empirical studies, ESEM, where it has been awarded the best paper award. ----------------------------------------------------------------------------------------------------------------------- 7. Full citation of the papers - Zamorano, M., Blasco, D., Cetina, C., & Sarro, F. (2025, April). Video Game Procedural Content Generation Through Software Transplantation. In International Conference on Software Engineering: Software Engineering in Practice. IEEE/ACM. - Zamorano, M., Domingo, Á., Cetina, C., & Sarro, F. (2024, October). Game software engineering: A controlled experiment comparing automated content generation techniques. In Proceedings of the 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (pp. 302-313). ----------------------------------------------------------------------------------------------------------------------- 8. Prize Money statement We will use the distribution agreed on the patent to split the prize money: Mar Zamorano: 34% África Domingo: 33% Daniel Blasco: 33% ----------------------------------------------------------------------------------------------------------------------- 9. A Statement Indicating Why this Entry Could Be the "Best" IMHOTEP, our evolutionary algorithm for procedural content transplantation, represents a novel and impactful advancement in the automatic generation of video game content. It is the first system to apply the principles of software transplantation, traditionally used in traditional software engineering, to the creative domain of game development. By leveraging a simulation-based fitness function rather than conventional test-suite compliance, IMHOTEP generates content that is not only functionally correct but also engaging, immersive, and meaningful from a player's perspective. Our approach has been empirically validated through an industrial case study (published at ICSE SEIP 2025) involving the commercial video game Kromaia, where 645 new non-playable characters were automatically generated by transplanting 129 distinct content elements into 5 different host. The results show that IMHOTEP produces content that is 2.5 times superior to state-of-the-art search-based procedural content generation techniques and 1.5 times superior to a variant of itself using standard fitness evaluation. Moreover, qualitative validation through a focus group of professional developers confirmed their satisfaction and willingness to adopt IMHOTEP-generated content in real-world production environments. In a complementary human-subject study, we also compared our transplantation approach with traditional Procedural Content Generation (PCG) across key quality metrics such as fun, design, and immersiveness. The study, involving 44 players and developers, revealed a clear preference for transplantation-generated content, challenging long-standing assumptions in game development about reusing content and opening up a new paradigm for content creation. This study has received the best paper award at ESEM 2024. The results achieved by IMHOTEP are not only technically superior but also scientifically robust and practically impactful. They represent a significant step forward in applying evolutionary computation to creative software content generation, a domain traditionally dominated by significant handcrafted human efforts. Our method enhances both developer productivity and player experience, while fostering novel forms of collaboration between humans and machines. We believe that IMHOTEP’s originality, demonstrated superiority over state-of-the-art solutions, and real-world applicability in a commercial game development pipeline make it the best entry for the Humies. Its success redefines what evolutionary algorithms can accomplish in creative, high-impact domains like game development. ----------------------------------------------------------------------------------------------------------------------- 10. Evolutionary Computation Type Evolutionary Programming ----------------------------------------------------------------------------------------------------------------------- 11. Publication Date - The first publication has been accepted at ICSE (SEIP) 2025, Ottawa, Canada. https://conf.researchr.org/track/icse-2025/icse-2025-software-engineering-in-practice?#Accepted-Papers - The second paper has been published at 24 October 2024