arXiv subjects

Simon T. Powers

Publications and source records attributed to Simon T. Powers.

At least 19 recordsLinked to original sources

arXiv2026

Trust or Check? Understanding the (Evolutionary) Dynamics of User Trust in AI Systems

As the capabilities and adoption of Artificial Intelligence (AI) systems grow, trust in these AI systems is an increasingly urgent concern. Much research has focused on models of AI governance and has primarily examined incentives for safe development and effective regulation. Hence they typically represented users trust as a one-shot adoption choice rather than as a dynamic, evolving process shaped by repeated interactions. We instead model trust as the dynamic choice of reduced monitoring in a repeated, asymmetric interaction between users and AI developers, where checking developers' behaviour is costly. Using evolutionary game theory, we study how users' strategies of trust and developers' strategies of providing safe (compliant) or unsafe (non-compliant) AI co-evolve under different levels of monitoring cost and institutional regimes. We conduct the analysis on both imitation-based and learning-based perspectives, with the stochastic finite-population dynamics, the infinite-population replicator analysis and the reinforcement learning analysis. We find three robust long-run regimes: no adoption by users while developers provide unsafe AI, unsafe but widely adopted systems, and safe systems that are widely adopted. Only the last is desirable, and it arises when penalties for unsafe behaviour exceed the extra cost of safety and users can still afford to monitor at least occasionally. Our results formally support governance proposals that emphasise transparency, low-cost monitoring, and meaningful sanctions, and they show that neither regulation alone nor blind user trust is sufficient to prevent the drift towards unsafe or low-adoption outcomes.

cs.AI↗

arXiv2026

Optimizing Appliance Scheduling for Solar Energy Management Using Metaheuristic Algorithms

Renewable energy is essential for meeting future energy demands; however, solar energy generation, which occurs only during daylight hours often does not align with household consumption patterns. Appliances such as cookers, washing machines, and dryers are typically operated according to user preferred schedules rather than solar energy availability, creating a scheduling optimization problem. The objective is to determine optimal appliance start times to maximize renewable energy utilization while minimizing user inconvenience and adhering to system constraints. This paper presents a metaheuristic approach using Iterated Local Search (ILS) and Simulated Annealing (SA) to optimize appliance start times, while considering appliance operating durations, power consumption, inverter limit, battery state of charge constraints, and solar generation forecasts. Unlike most existing work, the scheduling is extended beyond a single day to accommodate unfinished tasks from previous days (spillover), ensuring operational continuity and enabling sequential operation across multiple days. Experimental results show that the sequential multi-day scheduling framework effectively manages system constraints while ensuring user convenience under exclusive solar generation. These findings also open opportunities for future research on multi-objective trade-offs between investment in equipment of various sizes, return on that investment, and user satisfaction.

cs.AI↗

arXiv2026

Disentangling trust from cooperation: Evolution of trust as reduced monitoring in social dilemmas

It is commonly assumed that trust increases cooperation. However, game-theoretic models often fail to distinguish between cooperative actions and trust, making it difficult to independently measure trust and determine how its effects vary in different social dilemmas. To address this, we build on influential theories that equate trust with reduced monitoring of an agent's actions. We implement this as a heuristic that cognitively bounded agents can use in repeated games to avoid spending time and effort always monitoring their partner. Agents using this heuristic reduce monitoring of a partner's actions once a threshold level of cooperativeness has been observed -- providing a measurable and architecture-agnostic definition of trust. Using evolutionary game theory, we systematically analyse the success of strategies that use this trust heuristic across the entire space of two-player symmetric social dilemma games. We demonstrate that trust-as-reduced-monitoring facilitates cooperation in two different ways. First, when monitoring is costly, trust heuristics allow for higher levels of cooperation in social dilemmas where the temptation to defect is high. Second, when agents can make action errors, trust heuristics promote cooperation even in coordination problems. Our results disentangle trust from cooperation, and provide a behavioural measure of trust that applies across interaction types.

cs.GT↗

arXiv2025

Can Media Act as a Soft Regulator of Safe AI Development? A Game Theoretical Analysis

When developers of artificial intelligence (AI) products need to decide between profit and safety for the users, they likely choose profit. Untrustworthy AI technology must come packaged with tangible negative consequences. Here, we envisage those consequences as the loss of reputation caused by media coverage of their misdeeds, disseminated to the public. We explore whether media coverage has the potential to push AI creators into the production of safe products, enabling widespread adoption of AI technology. We created artificial populations of self-interested creators and users and studied them through the lens of evolutionary game theory. Our results reveal that media is indeed able to foster cooperation between creators and users, but not always. Cooperation does not evolve if the quality of the information provided by the media is not reliable enough, or if the costs of either accessing media or ensuring safety are too high. By shaping public perception and holding developers accountable, media emerges as a powerful soft regulator -- guiding AI safety even in the absence of formal government oversight.

cs.AI↗

arXiv2025

Do LLMs trust AI regulation? Emerging behaviour of game-theoretic LLM agents

There is general agreement that fostering trust and cooperation within the AI development ecosystem is essential to promote the adoption of trustworthy AI systems. By embedding Large Language Model (LLM) agents within an evolutionary game-theoretic framework, this paper investigates the complex interplay between AI developers, regulators and users, modelling their strategic choices under different regulatory scenarios. Evolutionary game theory (EGT) is used to quantitatively model the dilemmas faced by each actor, and LLMs provide additional degrees of complexity and nuances and enable repeated games and incorporation of personality traits. Our research identifies emerging behaviours of strategic AI agents, which tend to adopt more "pessimistic" (not trusting and defective) stances than pure game-theoretic agents. We observe that, in case of full trust by users, incentives are effective to promote effective regulation; however, conditional trust may deteriorate the "social pact". Establishing a virtuous feedback between users' trust and regulators' reputation thus appears to be key to nudge developers towards creating safe AI. However, the level at which this trust emerges may depend on the specific LLM used for testing. Our results thus provide guidance for AI regulation systems, and help predict the outcome of strategic LLM agents, should they be used to aid regulation itself.

cs.AI↗

arXiv2025

Media and responsible AI governance: a game-theoretic and LLM analysis

This paper investigates the complex interplay between AI developers, regulators, users, and the media in fostering trustworthy AI systems. Using evolutionary game theory and large language models (LLMs), we model the strategic interactions among these actors under different regulatory regimes. The research explores two key mechanisms for achieving responsible governance, safe AI development and adoption of safe AI: incentivising effective regulation through media reporting, and conditioning user trust on commentariats' recommendation. The findings highlight the crucial role of the media in providing information to users, potentially acting as a form of "soft" regulation by investigating developers or regulators, as a substitute to institutional AI regulation (which is still absent in many regions). Both game-theoretic analysis and LLM-based simulations reveal conditions under which effective regulation and trustworthy AI development emerge, emphasising the importance of considering the influence of different regulatory regimes from an evolutionary game-theoretic perspective. The study concludes that effective governance requires managing incentives and costs for high quality commentaries.

cs.AI↗

arXiv2024

Trust AI Regulation? Discerning users are vital to build trust and effective AI regulation

There is general agreement that some form of regulation is necessary both for AI creators to be incentivised to develop trustworthy systems, and for users to actually trust those systems. But there is much debate about what form these regulations should take and how they should be implemented. Most work in this area has been qualitative, and has not been able to make formal predictions. Here, we propose that evolutionary game theory can be used to quantitatively model the dilemmas faced by users, AI creators, and regulators, and provide insights into the possible effects of different regulatory regimes. We show that creating trustworthy AI and user trust requires regulators to be incentivised to regulate effectively. We demonstrate the effectiveness of two mechanisms that can achieve this. The first is where governments can recognise and reward regulators that do a good job. In that case, if the AI system is not too risky for users then some level of trustworthy development and user trust evolves. We then consider an alternative solution, where users can condition their trust decision on the effectiveness of the regulators. This leads to effective regulation, and consequently the development of trustworthy AI and user trust, provided that the cost of implementing regulations is not too high. Our findings highlight the importance of considering the effect of different regulatory regimes from an evolutionary game theoretic perspective.

cs.AI↗

arXiv2023

Promoting Social Behaviour in Reducing Peak Electricity Consumption Using Multi-Agent Systems

As we transition to renewable energy sources, addressing their inflexibility during peak demand becomes crucial. It is therefore important to reduce the peak load placed on our energy system. For households, this entails spreading high-power appliance usage like dishwashers and washing machines throughout the day. Traditional approaches to spreading out usage have relied on differential pricing set by a centralised utility company, but this has been ineffective. Our previous research investigated a decentralised mechanism where agents receive an initial allocation of time-slots to use their appliances, which they can exchange with others. This was found to be an effective approach to reducing the peak load when we introduced social capital, the tracking of favours, to incentivise agents to accept exchanges that do not immediately benefit them. This system encouraged self-interested agents to learn socially beneficial behaviour to earn social capital that they could later use to improve their own performance. In this paper we expand this work by implementing real world household appliance usage data to ensure that our mechanism could adapt to the challenging demand needs of real households. We also demonstrate how smaller and more diverse populations can optimise more effectively than larger community energy systems.

cs.MA↗

arXiv2022

Evolved Open-Endedness in Cultural Evolution: A New Dimension in Open-Ended Evolution Research

The goal of Artificial Life research, as articulated by Chris Langton, is "to contribute to theoretical biology by locating life-as-we-know-it within the larger picture of life-as-it-could-be" (1989, p.1). The study and pursuit of open-ended evolution in artificial evolutionary systems exemplifies this goal. However, open-ended evolution research is hampered by two fundamental issues; the struggle to replicate open-endedness in an artificial evolutionary system, and the fact that we only have one system (genetic evolution) from which to draw inspiration. Here we argue that cultural evolution should be seen not only as another real-world example of an open-ended evolutionary system, but that the unique qualities seen in cultural evolution provide us with a new perspective from which we can assess the fundamental properties of, and ask new questions about, open-ended evolutionary systems, especially in regard to evolved open-endedness and transitions from bounded to unbounded evolution. Here we provide an overview of culture as an evolutionary system, highlight the interesting case of human cultural evolution as an open-ended evolutionary system, and contextualise cultural evolution under the framework of (evolved) open-ended evolution. We go on to provide a set of new questions that can be asked once we consider cultural evolution within the framework of open-ended evolution, and introduce new insights that we may be able to gain about evolved open-endedness as a result of asking these questions.

cs.AI↗

arXiv2021

An Overview of Agent-based Traffic Simulators

Individual traffic significantly contributes to climate change and environmental degradation. Therefore, innovation in sustainable mobility is gaining importance as it helps to reduce environmental pollution. However, effects of new ideas in mobility are difficult to estimate in advance and strongly depend on the individual traffic participants. The application of agent technology is particularly promising as it focuses on modelling heterogeneous individual preferences and behaviours. In this paper, we show how agent-based models are particularly suitable to address three pressing research topics in mobility: 1. Social dilemmas in resource utilisation; 2. Digital connectivity; and 3. New forms of mobility. We then explain how the features of several agent-based simulators are suitable for addressing these topics. We assess the capability of simulators to model individual travel behaviour, discussing implemented features and identifying gaps in functionality that we consider important.

cs.MA↗

arXiv2020

When to (or not to) trust intelligent machines: Insights from an evolutionary game theory analysis of trust in repeated games

The actions of intelligent agents, such as chatbots, recommender systems, and virtual assistants are typically not fully transparent to the user. Consequently, using such an agent involves the user exposing themselves to the risk that the agent may act in a way opposed to the user's goals. It is often argued that people use trust as a cognitive shortcut to reduce the complexity of such interactions. Here we formalise this by using the methods of evolutionary game theory to study the viability of trust-based strategies in repeated games. These are reciprocal strategies that cooperate as long as the other player is observed to be cooperating. Unlike classic reciprocal strategies, once mutual cooperation has been observed for a threshold number of rounds they stop checking their co-player's behaviour every round, and instead only check with some probability. By doing so, they reduce the opportunity cost of verifying whether the action of their co-player was actually cooperative. We demonstrate that these trust-based strategies can outcompete strategies that are always conditional, such as Tit-for-Tat, when the opportunity cost is non-negligible. We argue that this cost is likely to be greater when the interaction is between people and intelligent agents, because of the reduced transparency of the agent. Consequently, we expect people to use trust-based strategies more frequently in interactions with intelligent agents. Our results provide new, important insights into the design of mechanisms for facilitating interactions between humans and intelligent agents, where trust is an essential factor.

cs.GT↗

arXiv2020

A mechanism to promote social behaviour in household load balancing

Reducing the peak energy consumption of households is essential for the effective use of renewable energy sources, in order to ensure that as much household demand as possible can be met by renewable sources. This entails spreading out the use of high-powered appliances such as dishwashers and washing machines throughout the day. Traditional approaches to this problem have relied on differential pricing set by a centralised utility company. But this mechanism has not been effective in promoting widespread shifting of appliance usage. Here we consider an alternative decentralised mechanism, where agents receive an initial allocation of time-slots to use their appliances and can then exchange these with other agents. If agents are willing to be more flexible in the exchanges they accept, then overall satisfaction, in terms of the percentage of agents time-slot preferences that are satisfied, will increase. This requires a mechanism that can incentivise agents to be more flexible. Building on previous work, we show that a mechanism incorporating social capital - the tracking of favours given and received - can incentivise agents to act flexibly and give favours by accepting exchanges that do not immediately benefit them. We demonstrate that a mechanism that tracks favours increases the overall satisfaction of agents, and crucially allows social agents that give favours to outcompete selfish agents that do not under payoff-biased social learning. Thus, even completely self-interested agents are expected to learn to produce socially beneficial outcomes.

cs.MA↗

arXiv2019

Status in flux: Unequal alliances can create power vacuums

Human groups show a variety of leadership structures from no leader, to changing leaders, to a single long-term leader. When a leader is deposed, the presence of a power vacuum can mean they are often quickly replaced. We lack an explanation of how such phenomena can emerge from simple rules of interaction between individuals. Here, we model transitions between different phases of leadership structure. We find a novel class of group dynamical behaviour where there is a single leader who is quickly replaced when they lose status, demonstrating a power vacuum. The model uses a dynamic network of individuals who non-coercively form and break alliances with one-another, with a key parameter modelling inequality in these alliances. We argue the model can explain transitions in leadership structure in the Neolithic Era from relatively equal hunter-gatherer societies, to groups with chieftains which change over time, to groups with an institutionalised leader on a paternal lineage. Our model demonstrates how these transitions can be explained by the impact of technological developments such as food storage and/or weapons, which meant that alliances became more unequal. In general terms, our approach provides a quantitative understanding of how technology and social norms can affect leadership dynamics and structures.

cs.SI↗

arXiv2019

Being a leader or being the leader: The evolution of institutionalised hierarchy

Human social hierarchy has the unique characteristic of existing in two forms. Firstly, as an informal hierarchy where leaders and followers are implicitly defined by their personal characteristics, and secondly, as an institutional hierarchy where leaders and followers are explicitly appointed by group decision. Although both forms can reduce the time spent in organising collective tasks, institutional hierarchy imposes additional costs. It is therefore natural to question why it emerges at all. The key difference lies in the fact that institutions can create hierarchy with only a single leader, which is unlikely to occur in unregulated informal hierarchy. To investigate if this difference can affect group decision-making and explain the evolution of institutional hierarchy, we first build an opinion-formation model that simulates group decision making. We show that in comparison to informal hierarchy, a single-leader hierarchy reduces (i) the time a group spends to reach consensus, (ii) the variation in consensus time, and (iii) the rate of increase in consensus time as group size increases. We then use this model to simulate the cost of organising a collective action which produces resources, and integrate this into an evolutionary model where individuals can choose between informal or institutional hierarchy. Our results demonstrate that groups evolve preferences towards institutional hierarchy, despite the cost of creating an institution, as it provides a greater organisational advantage which is less affected by group size and inequality.

q-bio.PE↗

arXiv2018

Can justice be fair when it is blind? How social network structures can promote or prevent the evolution of despotism

Hierarchy is an efficient way for a group to organize, but often goes along with inequality that benefits leaders. To control despotic behaviour, followers can assess leaders decisions by aggregating their own and their neighbours experience, and in response challenge despotic leaders. But in hierarchical social networks, this interactional justice can be limited by (i) the high influence of a small clique who are treated better, and (ii) the low connectedness of followers. Here we study how the connectedness of a social network affects the co-evolution of despotism in leaders and tolerance to despotism in followers. We simulate the evolution of a population of agents, where the influence of an agent is its number of social links. Whether a leader remains in power is controlled by the overall satisfaction of group members, as determined by their joint assessment of the leaders behaviour. We demonstrate that centralization of a social network around a highly influential clique greatly increases the level of despotism. This is because the clique is more satisfied, and their higher influence spreads their positive opinion of the leader throughout the network. Finally, our results suggest that increasing the connectedness of followers limits despotism while maintaining hierarchy.

q-bio.PE↗

arXiv2012

Punishment can promote defection in group-structured populations

Pro-social punishment, whereby cooperators punish defectors, is often suggested as a mechanism that maintains cooperation in large human groups. Importantly, models that support this idea have to date only allowed defectors to be the target of punishment. However, recent empirical work has demonstrated the existence of anti-social punishment in public goods games. That is, individuals that defect have been found to also punish cooperators. Some recent theoretical studies have found that such anti-social punishment can prevent the evolution of pro-social punishment and cooperation. However, the evolution of anti-social punishment in group-structured populations has not been formally addressed. Previous work has informally argued that group-structure must favour pro-social punishment. Here we formally investigate how two demographic factors, group size and dispersal frequency, affect selection pressures on pro- and anti-social punishment. Contrary to the suggestions of previous work, we find that anti-social punishment can prevent the evolution of pro-social punishment and cooperation under a range of group structures. Given that anti-social punishment has now been found in all studied extant human cultures, the claims of previous models showing the co-evolution of pro-social punishment and cooperation in group-structured populations should be re-evaluated.

q-bio.PE↗

arXiv2012

The efficacy of group selection is increased by coexistence dynamics within groups

Selection on the level of loosely associated groups has been suggested as a route towards the evolution of cooperation between individuals and the subsequent formation of higher-level biological entities. Such group selection explanations remain problematic, however, due to the narrow range of parameters under which they can overturn within-group selection that favours selfish behaviour. In principle, individual selection could act on such parameters so as to strengthen the force of between-group selection and hence increase cooperation and individual fitness, as illustrated in our previous work. However, such a process cannot operate in parameter regions where group selection effects are totally absent, since there would be no selective gradient to follow. One key parameter, which when increased often rapidly causes group selection effects to tend to zero, is initial group size, for when groups are formed randomly then even moderately sized groups lack significant variance in their composition. However, the consequent restriction of any group selection effect to small sized groups is derived from models that assume selfish types will competitively exclude their more cooperative counterparts at within-group equilibrium. In such cases, diversity in the migrant pool can tend to zero and accordingly variance in group composition cannot be generated. In contrast, we show that if within-group dynamics lead to a stable coexistence of selfish and cooperative types, then the range of group sizes showing some effect of group selection is much larger.

q-bio.PE↗

arXiv2012

How to measure group selection in real-world populations

Multilevel selection and the evolution of cooperation are fundamental to the formation of higher-level organisation and the evolution of biocomplexity, but such notions are controversial and poorly understood in natural populations. The theoretic principles of group selection are well developed in idealised models where a population is neatly divided into multiple semi-isolated sub-populations. But since such models can be explained by individual selection given the localised frequency-dependent effects involved, some argue that the group selection concepts offered are, even in the idealised case, redundant and that in natural conditions where groups are not well-defined that a group selection framework is entirely inapplicable. This does not necessarily mean, however, that a natural population is not subject to some interesting localised frequency-dependent effects -- but how could we formally quantify this under realistic conditions? Here we focus on the presence of a Simpson's Paradox where, although the local proportion of cooperators decreases at all locations, the global proportion of cooperators increases. We illustrate this principle in a simple individual-based model of bacterial biofilm growth and discuss various complicating factors in moving from theory to practice of measuring group selection.

q-bio.PE↗