Umeå University's logo

Modern computer games have become very complex, so they can benefit from automated testing. However, their huge and fine grained interaction space makes them very challenging for automated testing algorithms. Having a model of a system would greatly improve the effectiveness of a testing algorithm. However, manually constructing a model is expensive and time-consuming. This paper proposes an online agent-based search approach to solve common testing tasks for computer games, in particular games that involve elements of world navigation and exploration. On the fly, the approach also constructs a model of the system, which is then exploited to solve the given testing task. The effectiveness of the approach is studied via a case study called Lab Recruits and its simulation of another game called Dungeons and Dragons Online. The study showed that the approach is superior in its ability to complete testing tasks and its completion time compared to evolutionary algorithm, Q-learning and MCTS. This paper extends a previous work presented in ATEST by including evaluation on large game levels, evaluation of the achieved coverage and fault detection and the aforementioned comparison with other algorithms.

Values and context are important in an agent’s decision-making process. Individuals may prioritise values differently, and changing context can also necessitate different considerations. In this paper, we use Schwartz’s theory of basic human values to define ethical values and introduce a preorder to model an agent’s relative preference among those values. We characterise context using this preorder, which can then be used in socio-technical systems as part of the autonomous agents’ deliberation process. We also define the transition between contexts as shifts in value order. To illustrate our approach, we implement this preorder in a domestic water-consumption scenario featuring two towns whose citizens make daily decisions regarding showering, considering visitors, drought rules, and sports activities. Our results demonstrate how our model can effectively represent value orders and integrate them into agents’ decision-making processes. This approach also allows us to characterise contexts, understand how these contexts affect agents’ behaviour, and assess the impact of shifting contexts. We observe that the value order influences the dynamics of context transitions, making some value orders more prone to shift than others.

Human-AI coevolution, defined as a process in which humans and AI algorithms continuously influence each other, increasingly characterises our society, but is understudied in artificial intelligence and complexity science literature. Recommender systems and assistants play a prominent role in human-AI coevolution, as they permeate many facets of daily life and influence human choices through online platforms. The interaction between users and AI results in a potentially endless feedback loop, wherein users' choices generate data to train AI models, which, in turn, shape subsequent user preferences. This human-AI feedback loop has peculiar characteristics compared to traditional human-machine interaction and gives rise to complex and often “unintended” systemic outcomes. This paper introduces human-AI coevolution as the cornerstone for a new field of study at the intersection between AI and complexity science focused on the theoretical, empirical, and mathematical investigation of the human-AI feedback loop. In doing so, we: (i) outline the pros and cons of existing methodologies and highlight shortcomings and potential ways for capturing feedback loop mechanisms; (ii) propose a reflection at the intersection between complexity science, AI and society; (iii) provide real-world examples for different human-AI ecosystems; and (iv) illustrate challenges to the creation of such a field of study, conceptualising them at increasing levels of abstraction, i.e., scientific, legal and socio-political.

The United Nations (UN) put out a questionnaire and request for public comment on a proposal to form an Independent International Scientific Panel on Artificial Intelligence (AI), as well as a Global Dialogue on AI in the context of the Global Digital Compact. The questionnaire was sent out in late 2024, and the following brief report forms the response submitted by the AI Policy Lab at Umeå University, Sweden.

Theory of mind refers to the human ability to reason about the mental content of other people, such as their beliefs, desires, and goals. People use their theory of mind to understand, reason about, and explain the behaviour of others. Having a theory of mind is especially useful when people collaborate, since individuals can then reason on what the other individual knows as well as what reasoning they might do. Similarly, hybrid intelligence systems, where AI agents collaborate with humans, necessitate that the agents reason about the humans using computational theory of mind. However, to try to keep track of all individual mental attitudes of all other individuals becomes (computationally) very difficult. Accordingly, this paper provides a mechanism for computational theory of mind based on abstractions of single beliefs into higher-level concepts. These abstractions can be triggered by social norms and roles. Their use in decision making serves as a heuristic to choose among interactions, thus facilitating collaboration. We provide a formalization based on epistemic logic to explain how various inferences enable such a computational theory of mind. Using examples from the medical domain, we demonstrate how having such a theory of mind enables an agent to interact with humans effectively and can increase the quality of the decisions humans make.

Building software agents that make decisions based on human values presents a complex challenge. This is a first attempt to systematically review trends in how researchers represent, select, evaluate, and implement values in software agents. The review highlights two key limitations in the field. First, most research adopts or acknowledges Schwartz’s theory of basic human values, but often simplifies its complexity. Second, many studies oversimplify the notion of values in general, failing to utilize established theories from psychology or philosophy. Additionally, the review finds that common software tools and existing frameworks, like the Belief-Desire-Intention model, are frequently used without fully considering their underlying principles. This research offers valuable contributions to the field of value-based decision-making in software agents, exposing research gaps and limitations in current research, and highlighting the need for a more nuanced approach. By calling for researchers to integrate insights from economics, social science, psychology, and neuroscience, the review paves the way for the development of more sophisticated agents that can navigate the complexities of real-world decision-making.

Truly realistic models for policy making require multiple aspects of life, realistic social behaviour and the ability to simulate millions of agents. Current state of the art Agent-based models only achieve two of these requirements. Models that prioritise realistic social behaviour are not easily scalable because the complex deliberation takes into account all information available at each time step for each agent. Our framework uses context to considerably narrow down the information that has to be considered. A key property of the framework is that it can dynamically slide between fast deliberation and complex deliberation. Context is expanded based on necessity. We introduce the elements of the framework, describe the architecture and show a proof-of-concept implementation. We give first steps towards validation using this implementation.

Simulating for policy making can require modelling multiple aspects of life, realistic social behaviour and the ability to simulate up to millions of agents [1]. However realistic models are not easily scalable due to the complex deliberation that takes into account all information at every time step which is slow. Explicitly taking into account context in the deliberation can increase scalability, through a complexity by need principle. The Dynamic Context-Sensitive Deliberation (DCSD) framework uses minimal information when possible, but gradually draws in more information when necessary. To validate whether DCSD can increase scalability while retaining realism we implement DCSD into an example large scale model, the Agent-based Social Simulation of the Coronavirus Crisis (ASSOCC). We compare the original deliberation from the ASSOCC model with the implemented DCSD. We conclude that DCSD can increase scalability while retaining realism in large scale social simulation models.

In order to enhance collaboration between humans and artificially intelligent agents, it is crucial to equip the computational agents with capabilities commonly used by humans. One of these capabilities is called Theory of Mind (ToM) reasoning, which is the human ability to reason about the mental contents of others, such as their beliefs, desires, and goals. For an agent to efficiently benefit from having a functioning computational ToM of its human partner in a collaboration, it needs to be practical in computationally tracking their mental attitudes and it needs to create approximate ToM models that can be effectively maintained. In this paper, we propose a computational ToM mechanism based on abstracting beliefs and knowledge into higher-level human concepts, referred to as abstractions. These abstractions, similar to those guiding human interactions (e.g., trust), form the basis of our modular agent architecture. We address an important challenge related to maintaining abstractions effectively, namely abstraction consistency. We propose different approaches to study this challenge in the context of a scenario inspired by a medical domain and provide an experimental evaluation over agent simulations.

As the game industry continues to evolve in pop-ularity, testing the experience of players becomes crucial for attracting and retaining players in the highly competitive market. However, the absence of automated methods for articulating and verifying player experience (PX) specifications led us to introduce EmoSTL, a specialized language that extends Linear Temporal Logic with spatial and time-interval expressions, enabling the capture of complex temporal and spatial aspects of players' emotions and their experiences within games. We conducted a user study to collect suggestive PX requirements for a game under test to assess the capabilities of EmoSTL. Findings reveal that the language formalizes 92 percent of the set PX requirements, and with runtime verification, several PX design issues are iden-tified in the game. Moreoever, EmoSTL performance evaluation demonstrates its linear execution time, showcasing the language potential usage in automated PX testing of games.