Large language models (LLMs) offer promise for dynamic game content generation, but they face critical barriers, including narrative incoherence and high operational costs. Due to their large size, they are often accessed in the cloud, limiting their application in offline games. Many of these practical issues are solved by pivoting to small language models (SLMs), but existing studies using SLMs have resulted in poor output quality. We propose a strategy of achieving high-quality SLM generation through aggressive fine-tuning on deliberately scoped tasks with narrow context, constrained structure, or both. In short, more difficult tasks require narrower scope and higher specialization to the training corpus. Training data is synthetically generated via a DAG-based approach, grounding models in the specific game world. Such models can form the basis for agentic networks designed around the narratological framework at hand, representing a more practical and robust solution than cloud-dependent LLMs. To validate this approach, we present a proof-of-concept focusing on a single specialized SLM as the fundamental building block. We introduce a minimal RPG loop revolving around rhetorical battles of reputations, powered by this model. We demonstrate that a simple retry-until-success strategy reaches adequate quality (as defined by a rubric-based LLM-as-a-judge scheme) with predictable latency suitable for real-time generation. Generation time estimates based on human annotation and cross-model validation suggest that the retry strategy remains practical even under substantially stricter quality requirements for the quantized models. While local quality assessment remains an open question, our results demonstrate feasibility for real-time generation under typical game engine constraints.

Cheating in online video games compromises the integrity of gaming experiences. Anti-cheat systems, such as VAC (Valve Anti-Cheat), face significant challenges in keeping pace with evolving cheating methods without imposing invasive measures on users' systems. This paper presents AntiCheatPT_256, a transformer-based machine learning model designed to detect cheating behaviour in Counter-Strike 2 using gameplay data. To support this, we introduce and publicly release CS2CD: A labelled dataset of$\mathbf{7 9 5}$matches. Using this dataset,$\mathbf{9 0, 7 0 7}$context windows were created and subsequently augmented to address class imbalance. The transformer model, trained on these windows, achieved an accuracy of 89.17 % and an AUC of 93.36 % on an unaugmented test set. This approach emphasizes reproducibility and real-world applicability, offering a robust baseline for future research in data-driven cheat detection.

This study investigates the psychophysiological effects of loot box interactions in video games and their potential similarities to those recorded during gambling interactions. Using electrodermal activity (EDA) measurements, the research examines player arousal during loot box interactions and explores the relationship between Internet Gaming Disorder (IGD) severity and loot box interactions from a psychophysiological perspective. The study employs a custom-designed game to control experimental conditions and standardise loot box interactions. Participants' IGD severity is assessed using the Internet Gaming Disorder Scale - Short Form (IGDS9-SF), while arousal is measured through EDA, analysing both tonic and phasic components. The study contributes to the ongoing debate surrounding gaming disorder and loot boxes, offering insights for game developers and policymakers on the potential risks associated with random reward mechanisms in video games.

This paper proposes a structured methodology to evaluate AI-generated game narratives, leveraging the Delphi study structure with a panel of narrative design experts. Our approach synthesizes story quality dimensions from literature and expert insights, mapping them into the Kano model framework to understand their impact on player satisfaction. The results can inform game developers on prioritizing quality aspects when co-creating game narratives with generative AI.

Video game designers often view confusion as undesirable, yet it is inevitable, as new players must adapt to new interfaces and mechanics in an increasingly varied and innovative game market, which is more popular than ever. Research suggests that confusion can contribute to a positive experience, potentially motivating players to learn. The state of confusion in video games should be further investigated to gain more insight into the learning experience of play and how it affects the player experience. In this article, we design a study to collect learning-related affects for users playing a game prototype that intentionally confuses the player. We assess the gathered affects against a complex learning model, affirming that, in specific instances, the player experience aligns with the learning experiences. Moreover, we identify correlations between these affects and the Player Experience Inventory constructs, particularly concerning flow experiences.

Facial mimicry—the automatic, unconscious imitation of others’ expressions—is vital for emotional understanding. This study investigates how mimicry differs across emotions using Face Action Units from videos and participants’ responses. Dynamic Time Warping quantified the temporal alignment between participants’ and stimuli’s facial expressions, revealing significant emotional variations. Post-hoc tests indicated greater mimicry for ’Fear’ than ’Happy’ and reduced mimicry for ’Anger’ compared to ’Fear’. The mimicry correlations with personality traits like Extraversion and Agreeableness were significant, showcasing subtle yet meaningful connections. These findings suggest specific emotions evoke stronger mimicry, with personality traits playing a secondary role in emotional alignment. Notably, our results highlight how personality-linked mimicry mechanisms extend beyond interpersonal communication to affective computing applications, such as remote humanhuman interactions and human-virtual-agent scenarios. Insights from temporal facial mimicry—e.g., designing digital agents that adaptively mirror user expressions—enable developers to create empathetic, personalized systems, enhancing emotional resonance and user engagement.

Videogames have been a catalyst for advances in many research fields, such as artificial intelligence, human-computer interaction, or virtual reality. Over the years, research in fields such as artificial intelligence has enabled the design of new types of games, while games have often served as a powerful tool for testing and simulation. Can this also happen with neuroscience? What is the current relationship between neuroscience and games research? what can we expect from the future? In this article, we will try to answer these questions, analysing the current state-of-the-art at the crossroads between neuroscience and games and envisioning future directions.

The Uncanny Valley phenomenon refers to the feeling of unease that arises when interacting with characters that appear almost, but not quite, human-like. First theorised by Masahiro Mori in 1970, it has since been widely observed in different contexts from humanoid robots to video games, in which it can result in players feeling uncomfortable or disconnected from the game, leading to a lack of immersion and potentially reducing the overall enjoyment. The phenomenon has been observed and described mostly through behavioural studies based on self-reported scales of uncanny feeling: however, there is still no consensus on its cognitive and perceptual origins, which limits our understanding of its impact on player experience. In this paper, we present a study aimed at identifying the mechanisms that trigger the uncanny response by collecting and analysing both self-reported feedback and EEG data.

Game difficulty is a crucial aspect of game design, that can be directly influenced by tweaking game mechanics. Perceived difficulty can however also be influenced by simply altering the graphics to something more threatening. Here, we present a study with 12 participants playing 4 different minigames with either altered graphics or mechanics to make the game more difficult. Using EEG bandpower analysis, we find that frontal lobe activity is heightened in all 4 of the mechanically challenging versions and 2/4 of the visually altered versions, all differences that do not emerge from the self-reported player experience. This suggests that EEG could aid researchers with a more sensitive tool for investigating challenge in games.

This paper focuses on procedurally generating rules and communicating them to players to adjust the difficulty. This is part of a larger project to collect and adapt games in educational games for young children using a digital puzzle game designed for kindergarten. A genetic algorithm is used together with a difficulty measure to find a target number of solution sets and a large language model is used to communicate the rules in a narrative context. During testing the approach was able to find rules that approximate any given target difficulty within two dozen generations on average. The approach was combined with a large language model to create a narrative puzzle game where players have to host a dinner for animals that can’t get along. Future experiments will try to improve evaluation, specialize the language model on children’s literature, and collect multi-modal data from players to guide adaptation.

The accurate and personalized estimation of task difficulty provides many opportunities for optimizing user experience. However, user diversity makes such difficulty estimation hard, in that empirical measurements from some user sample do not necessarily generalize to others.

Successful and accurate modelling of level difficulty is a fundamental component of the operationalisation of player experience as difficulty is one of the most important and commonly used signals for content design and adaptation. In games that feature intermediate milestones, such as completable areas or levels, difficulty is often defined by the probability of completion or completion rate; however, this operationalisation is limited in that it does not describe the behaviour of the player within the area. In this research work, we formalise a model of level difficulty for puzzle games that goes beyond the classical probability of success. We accomplish this by describing the distribution of actions performed within a game level using a parametric statistical model thus creating a richer descriptor of difficulty. The model is fitted and evaluated on a dataset collected from the game Lily's Garden by Tactile Games, and the results of the evaluation show that the it is able to describe and explain difficulty in a vast majority of the levels.

In this work we investigate whether it is plausible to use the performance of a reinforcement learning (RL) agent to estimate the difficulty measured as the player completion rate of different levels in the mobile puzzle game Lily's Garden.For this purpose we train an RL agent and measure the number of moves required to complete a level. This is then compared to the level completion rate of a large sample of real players.We find that the strongest predictor of player completion rate for a level is the number of moves taken to complete a level of the ~5% best runs of the agent on a given level. A very interesting observation is that, while in absolute terms, the agent is unable to reach human-level performance across all levels, the differences in terms of behaviour between levels are highly correlated to the differences in human behaviour. Thus, despite performing sub-par, it is still possible to use the performance of the agent to estimate, and perhaps further model, player metrics.

In this article, we present an experimental approach to using parameterized Generative Adversarial Networks (GANs) to produce levels for the puzzle game Lily’s Garden1. We extract two condition-vectors from the real levels in an effort to control the details of the GAN’s outputs. While the GANs performs well in approximating the first condition (map-shape), they struggle to approximate the second condition (piece distribution). We hypothesize that this might be improved by trying out alternative architectures for both the Generator and Discriminator of the GANs.

While traditionally a labour intensive task, the testing of game content is progressively becoming more automated. Among the many directions in which this automation is taking shape, automatic play-testing is one of the most promising thanks also to advancements of many supervised and reinforcement learning (RL) algorithms. However these type of algorithms, while extremely powerful, often suffer in production environments due to issues with reliability and transparency in their training and usage.

In freemium games, the revenue from a player comes from the in-app purchases made and the advertisement to which that player is exposed. The longer a player is playing the game, the higher will be the chances that he or she will generate a revenue within the game. Within this scenario, it is extremely important to be able to detect promptly when a player is about to quit playing (churn) in order to react and attempt to retain the player within the game, thus prolonging his or her game lifetime. In this article we investigate how to improve the current state-of-the-art in churn prediction by combining sequential and aggregate data using different neural network architectures. The results of the comparative analysis show that the combination of the two data types grants an improvement in the prediction accuracy over predictors based on either purely sequential or purely aggregated data.

In a three-dimensional virtual environment, aspects such as narrative and interaction largely depend on the placement and animation of the virtual camera. Therefore, virtual camera control plays a critical role in player experience and, thereby, in the overall quality of a computer game. Both game industry and game AI research focus on the development of increasingly sophisticated systems to automate the control of the virtual camera integrating artificial intelligence algorithms within physical simulations. However, in both industry and academia little research has been carried out on the relationship between virtual camera, game-play and player behaviour. We run a game user experiment to shed some light on this relationship and identify relevant differences between camera behaviours through different game sessions, playing behaviours and player gaze patterns. Results show that users can be efficiently profiled in dissimilar clusters according to camera control as part of their gameplay behaviour.

This paper presents a fast and reliable global-search approach to the problem of virtual camera positioning when multiple objects that need to be within the reach of the camera are fully occluded. For this purpose, a comparative analysis of global-search algorithms is presented for the problem of maximising camera visibility across different tasks of varying complexity and within different real-time windows. A custom-designed genetic algorithm is compared to octree-based search and random search and results showcase the advantages of the genetic algorithm proposed with respect to efficiency, robustness and computational effort.