ДОСЛІДЖЕННЯ ТА РОЗРОБКА ПРОГРАМНИХ ПОВЕДІНКОВИХ КОМПОНЕНТ В КОМП’ЮТЕРНИХ ІГРОВИХ СИСТЕМАХ

Creating engaging interactive story-based experiences dynamically responding to individual player choices poses significant challenges for narrative-centered games. Recent advances in pre-trained large language models (LLMs) have the potential to revolutionize procedural content generation for narrative-centered games. Historically, interactive narrative generation has specified pivotal events in the storyline, often utilizing planning-based approaches toward achieving narrative coherence and maintaining the story arc. However, manual authorship is typically used to create detail and variety in non-player character (NPC) interaction to specify and instantiate plot events. This paper proposes SCENECRAFT, a narrative scene generation framework that automates NPC interaction crucial to unfolding plot events. SCENECRAFT interprets natural language instructions about scene objectives, NPC traits, location, and narrative variations. It then employs large language models to generate game scenes aligned with authorial intent. It generates branching conversation paths that adapt to player choices while adhering to the author’s interaction goals. LLMs generate interaction scripts, semantically extract character emotions and gestures to align with the script, and convert dialogues into a game scripting language. The generated script can then be played utilizing an existing narrative-centered game framework. Through empirical evaluation using automated and human assessments, we demonstrate SCENECRAFT’s effectiveness in creating narrative experiences based on creativity, adaptability, and alignment with intended author instructions.

This paper firstly seeks an answer to the question of whether Non Player Characters (NPCs) in Computer Games can also be viewed as game agents where reactivity, autonomy, being temporarily continuous and having goal-oriented behavior are taken as the features of being a game agent. Within this scope, we will try to assess whether naming NPCs as agents point to a desire that one day they would fulfill the requirements of being an agent or whether NPCs actually already fulfill these requirements. Secondly, the paper looks into the AI needs of video games. We present the AI methodologies that are either being used and under research for use in Game AI. The same methodologies are also likely to contribute to the increasing levels of autonomy and goal-directed behavior of NPCs and help them become more agent-like.

Abstract: Applications of fuzzy logic in game creation have proven useful, especially when it comes to modelling the behavior of non-player characters (NPCs) in video games. NPC behavior in video games has historically been governed by strict rule-based systems or scripted sequences, which frequently led to restricted and predictable interactions. On the other hand, fuzzy logic adds a degree of flexibility and ambiguity to the decision-making processes of NPCs. By improving the naturalness, adaptability, and emotional resonance of NPC behavior, fuzzy logic may greatly enhance player experiences in games. It provides players with progressively more engaging and dynamic gaming experiences as it continues to be incorporated into game production, opening up new possibilities for interactive narrative, gaming, and immersive virtual worlds. Based on Utku Kose's article, "Developing a Fuzzy Logic Based Game System," I have investigated the use of fuzzy logic in gaming contexts for NPC decision-making in this study.

This article explores various applications of artificial intelligence (AI) technologies in dairy farming, including the use of computer vision systems (CVS) for animal identification, BCS and body shape analysis, and potential uses of large language models (LLM) in the dairy industry. Among recent advancements in precision livestock farming tools, CVS have gained popularity as powerful solutions for individual animal monitoring. These systems can capture phenotypes from multiple animals simultaneously using a single device in an automated and nonintrusive manner. To match animals with their corresponding predicted phenotypes, these systems require individual animal identification, which can be achieved through external identification systems or computer vision-based animal identification algorithms. Additionally, modern natural language processing techniques, such as LLM, offer opportunities for advanced data integration, including unstructured textual data. Furthermore, we discuss the challenges associated with integrating data from different sources and modalities, such as images, text, and tabular data, into multimodal machine learning systems for phenotype prediction, which also represents a key area of AI application. Digital technologies such as CVS and LLM have the potential to transform dairy farming; CVS can provide individual and objective assessments of animal health, whereas LLM can integrate diverse data sources for phenotype prediction. Although there are many potential challenges ahead, these technologies offer significant opportunities for advancing animal health monitoring, farm management, and individual phenotyping.

Creating the behavior for non-player characters in video games is a complex task that requires the collaboration among programmers and game designers.

Non-playable Character (NPC) is one of the important characters in the game. An autonomous and adaptive NPC can adjust actions with player actions and environmental conditions. To determine the actions of the NPC, the previous researchers used the Neural Network method but there were weaknesses, namely the action produced was not in accordance with the desired so the accuracy was not good. This study overcomes the problem of poor accuracy by using the Logarithmic Learning for Generalized Classifier Neural Network (L-GCNN) method with 6 input parameters, NPC health, distance from players, other NPCs involved, attack power, number of NPCs and NPC levels. While the output is to attack itself, attack in groups and move away. For testing, this study was tested on RPG games. From the results of the experiments conducted, it shows that the L-GCNN method has better accuracy than the 3 methods compared to 7% better than NN and SVM and 8% better than RBFNN because in the L-GCNN method there is an encapsulation process that is data have the same class will. Whereas the L-GCNN training time is 30% longer than the NN method because on L-GCNN one neuron consists of one data where there are fewer NNs in the hidden layer.

Nowadays, video games conforms a huge industry that is always developing new technology. In particular, artificial intelligence techniques have been used broadly in the well-known non-player characters (NPC) given the opportunity to users to feel video games more real. This paper proposes the usage of the MaxQ-Q hierarchical reinforcement learning algorithm in non-player characters in order to increase the experience of the user in terms of naturalness. A case study of an NPC with the proposed artificial intelligence based algorithm in a first personal shooter video game was developed. Experimental results show that this implementation improves naturalness from the user’s point of view. In addition, the proposed MaxQ-Q based algorithm in NPCs allow to programmers a robust way to give artificial intelligence to them.

Many serious games use dialogue between players and non-player characters (NPCs) to enhance learning.However, designing appropriate dialogue is often time-consuming for game developers. Recent advancements in artificialintelligence, particularly Large Language Models (LLMs), have made open-ended dialogue with virtual characters feasible,though managing it in educational contexts remains a significant challenge. This study explores how game designers canguide open-ended dialogue powered by LLMs to create meaningful educational conversations. Expert interviews and areview of existing approaches to implementing open-ended conversation in games led to the formulation of designrequirements for a new framework. Based on these insights, the Behaviour-Driven Conversational Prompting (BDCP)framework was developed. This framework offers practical guidance for designers to create scenarios where behaviourallearning objectives are achieved through structured dialogue. It combines lock-and-key narrative design, dynamic characterprompts that dictate LLM-generated responses, and behaviour analysis prompts that assess player interactions. To validatethe framework, a functional prototype called ‘Detective Duck’ was created. This detective-style 'whodunit' game has playerssolve crimes through open-ended conversation with AI-driven characters. Players encounter challenges such as persuadinghesitant witnesses, or verifying alibis. These challenges can only be solved by demonstrating reasoning and conversationalstrategies relevant for detectives such as lateral thinking and persuasion. Upon demonstrating these behaviours, characterprompts can be dynamically adjusted, ensuring that - only then - players receive key clues needed to advance the narrative.The framework and prototype were evaluated against the established design requirements and through expert interviews.Results were largely positive, indicating that the BDCP framework supports meaningful, open-ended dialogue aligned witheducational objectives. However, some inconsistencies in dialogue coherence and adherence to designer intent were noted.Future work will focus on refining narrative consistency and enhancing adherence to designer intent by fine-tuning thelanguage model, integrating AI-driven player feedback, and incorporating other game mechanics into the framework. Theseimprovements would further strengthen the BDCP framework as a tool for designing serious games centered around openendedconversation.

Physicians frequently confront time-sensitive decisions under uncertain conditions, necessitating reliable tools for forecasting clinical outcomes. Although clinical predictive models have the potential to assist in these critical decisions, their widespread adoption is hindered by complexities in data handling, model development, and integration into clinical workflows. This study introduces a novel framework (Hopkins LLM) leveraging structured electronic health records (EHRs) data to develop and deploy clinical large language models (LLMs) that act as multi-task-capable predictive engines to support clinically constrained decision-support tasks with minimal barriers to implementation. Employing the advanced LLaMA architecture, consisting of 7 billion parameters, our model was pre-trained on a comprehensive corpus and subsequently fine-tuned and tested on a dataset of 42,160 patients within Johns Hopkins Health System, addressing a spectrum of clinical and operational prediction tasks. We validated our model across three diverse external health systems and four key prediction tasks involving 1,329 patients, including 30-day all-cause readmissions, 90-day all-cause mortality, 30-day intensive care unit (ICU) admissions, and treatment recommendations. The proposed Hopkins-LLM framework achieved a mean area under the receiver operating characteristic curve (ROC-AUC) of 0.84 [0.82, 0.88], yielding a significant 0.28 advancement over zero-shot baseline LLMs (p<0.05). These findings underscore the promise of LLMs as unified, user-friendly clinical prediction systems, adept at reasoning across diverse data sources to enhance decision-making at the point of care.

Authoring the AI for non-player characters (NPCs) in modern video games is an increasingly complex task. Designers and programmers must collaborate to resolve a tension between believable agents with emergent behaviours and scripted story lines. Behaviour trees (BTs) have been proposed as an expressive mechanism that let designers create complex behaviours along the lines of the story they want to tell. However, BTs are still too complex for non-programmers. In this paper, we propose the use of plan traces to assist designers when building BTs. In order to make this approach feasible within state-of-the-art video game technology, we generate the planning domain through an extension of the component-based approach, a widely used technique for representing entities in commercial video games.

Typically, the creation of AI-based behaviors for Non-Playing Characters (NPC) in computer games is carried out by people with specialized skills in the broad areas of design and programming. This book chapter presents Second Mind (SM), a digital solution that makes it possible for novice users to successfully author behaviors. In SM, authors can use a graphical interface to define the behaviors of virtual characters in response to interactions with players. Authors can easily endow NPCs with behavior capabilities that make them act in different possible roles such as e.g. shopkeepers, museum hosts, etc. A series of user tests with human subjects to evaluate the behavior authoring process shows that Second Mind is easy to understand and simplifies the process of behavior production.

Non-Player Characters (NPCs) are a vital part of computer games. Their behaviour is usually pre determined by the developers before a computer game is released. While these NPCs exist in a virtual environment in which they aim to achieve their objectives, these objectives might involve certain actions which should be both believable and add realism to games. In internet gameplay, these may range from navigation of the environment, attack and defense of an objective or assisting other NPCs or human players to achieve their goals. Various forms of decision making process are now implemented to provide believability and realism to games. These techniques range from reinforcement learning, imitation learning, supervised and unsupervised learning for online and offline games. While these are widely implemented, a new genre of realism is being added to games especially first person shooter games, namely Smart Terrains with virtual destructive environments. Smart Terrain has the potential to improve the realism of games and the behavior of the NPC in games such as first person shooter games where gameplay is fast paced. The potential issue would be if NPCs are dynamic enough to recognize changes in the virtual environment or if the virtual environment provides the required information to assist the NPCs with their objectives or tasks. This paper presents an overview of Smart Terrain in enhancing Online Tactic Agent decision making.

Creating the behavior for non-player characters (NPCs) in video games is a complex task that requires the collaboration among programmers and game designers. Usually these game designers are responsible of configuring and fine tuning certain parameters of the behavior, while programmers write the actual code of those behaviors. That requires several iterations between them. In this paper, we present a new approach for creating the behavior of NPCs that gives more power to the game designer to create behavior without technical knowledge using program by demonstration but preserving the designer confident of the final behavior.

Imagine a scenario in which players engage in conversations with non-playable characters (NPCs) in video games using a microphone, free from scripted responses or predefined constraints. With the advancement of Generative Artificial Intelligence (GAI), this possibility has become more feasible than ever. This article examines the Mantella mod for The Elder Scrolls V: Skyrim (Bethesda, 2011), which facilitates natural language interactions with NPCs, transforming player engagement within the game’s fictional universe. Skyrim is an action role-playing game (RPG) developed by Bethesda Game Studios. With over 60 million copies sold and releases spanning three generations of gaming consoles, Skyrim has cemented its place in gaming history. A significant factor contributing to its enduring relevance is its vibrant modding community, which has enabled players to modify and expand the game in myriad ways – ranging from graphical enhancements to the introduction of new areas and survival mechanics. This extensive capacity for customization has sustained the game’s popularity for over a decade since its initial release. The primary objective of this article is to investigate the creative appropriation of GAI by Skyrim's PC modding community. Specifically, it addresses the following question: What AI imaginaries emerge from Skyrim gameplay influenced by the Mantella mod? To explore this question, 13 YouTube videos were collected using ethnographic techniques, complemented by a formal gameplay analysis.

The combination of gamification and agent systems based on Large Language Models (LLMs) presents a great opportunity in the design of adaptable, interactive systems that offer engagement and personalized interactions. In this systematic literature review, we examine the state of the art at this intersection, drawing on 11 studies published from 2019 to 2025, using the PRISMA 2020 framework, and investigating the following seven research questions related to: publication trends, areas of application, agent roles, gamification strategies, design goals, and limitations. We find LLM agents are being deployed across multiple application areas in gamified systems, in the fields of education, mental health, cyber defense, and commerce, while functioning in multiple roles such as tutors, an emotional companions, and being involved in the co-design process. Yet, we identified key challenges including weak connectivity between gamification mechanics and agents' behaviors and capabilities, limited longitudinal evaluation, and ethical concerns for LLMs related to persuasion and autonomy of the user. Our review provides a foundation for furthering the study and development of gamification systems involving LLM agents.