arXiv subjects

Theodor Cimpeanu

Publications and source records attributed to Theodor Cimpeanu.

15 recordsLinked to original sources

arXiv2026

Evolution of fairness in hybrid populations with specialised AI agents

Fairness in hybrid societies hinges on a simple choice: should AI be a generous host or a strict gatekeeper? Moving beyond symmetric models, we show that asymmetric social structures--like those in hiring, regulation, and negotiation--AI that guards fairness outperforms AI that gifts it. We bridge this gap with a bipartite hybrid population model of the Ultimatum Game, separating humans and AI into distinct proposer and receiver groups. We first introduce Samaritan AI agents, which act as either unconditional fair proposers or strict receivers. Our results reveal a striking asymmetry: Samaritan AI receivers drive population-wide fairness far more effectively than Samaritan AI proposers. To overcome the limitations of the Samaritan AI proposer, we design the Discriminatory AI proposer, which predicts co-players' expectations and only offers fair portions to those with high acceptance thresholds. Our results demonstrate that this Discriminatory AI outperforms both types of Samaritan AI, especially in strong selection scenarios. It not only sustains fairness across both populations but also significantly lowers the critical mass of agents required to reach an equitable steady state. By transitioning from unconditional modelling to strategic enforcement, our work provides a pivotal framework for deploying asymmetric AIs in the increasingly hybrid society.

cs.MA↗

arXiv2025

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↗

arXiv2025

Multi-Agent Risks from Advanced AI

The rapid development of advanced AI agents and the imminent deployment of many instances of these agents will give rise to multi-agent systems of unprecedented complexity. These systems pose novel and under-explored risks. In this report, we provide a structured taxonomy of these risks by identifying three key failure modes (miscoordination, conflict, and collusion) based on agents' incentives, as well as seven key risk factors (information asymmetries, network effects, selection pressures, destabilising dynamics, commitment problems, emergent agency, and multi-agent security) that can underpin them. We highlight several important instances of each risk, as well as promising directions to help mitigate them. By anchoring our analysis in a range of real-world examples and experimental evidence, we illustrate the distinct challenges posed by multi-agent systems and their implications for the safety, governance, and ethics of advanced AI.

cs.MA↗

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

Fairness and Deception in Human Interactions with Artificial Agents

Online information ecosystems are now central to our everyday social interactions. Of the many opportunities and challenges this presents, the capacity for artificial agents to shape individual and collective human decision-making in such environments is of particular importance. In order to assess and manage the impact of artificial agents on human well-being, we must consider not only the technical capabilities of such agents, but the impact they have on human social dynamics at the individual and population level. We approach this problem by modelling the potential for artificial agents to "nudge" attitudes to fairness and cooperation in populations of human agents, who update their behavior according to a process of social learning. We show that the presence of artificial agents in a population playing the ultimatum game generates highly divergent, multi-stable outcomes in the learning dynamics of human agents' behaviour. These outcomes correspond to universal fairness (successful nudging), universal selfishness (failed nudging), and a strategy of fairness towards artificial agents and selfishness towards other human agents (unintended consequences of nudging). We then consider the consequences of human agents shifting their behavior when they are aware that they are interacting with an artificial agent. We show that under a wide range of circumstances artificial agents can achieve optimal outcomes in their interactions with human agents while avoiding deception. However we also find that, in the donation game, deception tends to make nudging easier to achieve.

q-bio.PE↗

arXiv2023

The evolutionary advantage of guilt: co-evolution of social and non-social guilt in structured populations

Building ethical machines may involve bestowing upon them the emotional capacity to self-evaluate and repent on their actions. While apologies represent potential strategic interactions, the explicit evolution of guilt as a behavioural trait remains poorly understood. Our study delves into the co-evolution of two forms of emotional guilt: social guilt entails a cost, requiring agents to exert efforts to understand others' internal states and behaviours; and non-social guilt, which only involves awareness of one's own state, incurs no social cost. Resorting to methods from evolutionary game theory, we study analytically, and through extensive numerical and agent-based simulations, whether and how guilt can evolve and deploy, depending on the underlying structure of the systems of agents. Our findings reveal that in lattice and scale-free networks, strategies favouring emotional guilt dominate a broader range of guilt and social costs compared to non-structured well-mixed populations, so leading to higher levels of cooperation. In structured populations, both social and non-social guilt can thrive through clustering with emotionally inclined strategies, thereby providing protection against exploiters, particularly for less costly non-social strategies. These insights shed light on the complex interplay of guilt and cooperation, enhancing our understanding of ethical artificial intelligence.

cs.MA↗

arXiv2023

Does Spending More Always Ensure Higher Cooperation? An Analysis of Institutional Incentives on Heterogeneous Networks

Humans have developed considerable machinery used at scale to create policies and to distribute incentives, yet we are forever seeking ways in which to improve upon these, our institutions. Especially when funding is limited, it is imperative to optimise spending without sacrificing positive outcomes, a challenge which has often been approached within several areas of social, life and engineering sciences. These studies often neglect the availability of information, cost restraints, or the underlying complex network structures, which define real-world populations. Here, we have extended these models, including the aforementioned concerns, but also tested the robustness of their findings to stochastic social learning paradigms. Akin to real-world decisions on how best to distribute endowments, we study several incentive schemes, which consider information about the overall population, local neighbourhoods, or the level of influence which a cooperative node has in the network, selectively rewarding cooperative behaviour if certain criteria are met. Following a transition towards a more realistic network setting and stochastic behavioural update rule, we found that carelessly promoting cooperators can often lead to their downfall in socially diverse settings. These emergent cyclic patterns not only damage cooperation, but also decimate the budgets of external investors. Our findings highlight the complexity of designing effective and cogent investment policies in socially diverse populations.

cs.MA↗

arXiv2022

Social Diversity Reduces the Complexity and Cost of Fostering Fairness

Institutions and investors are constantly faced with the challenge of appropriately distributing endowments. No budget is limitless and optimising overall spending without sacrificing positive outcomes has been approached and resolved using several heuristics. To date, prior works have failed to consider how to encourage fairness in a population where social diversity is ubiquitous, and in which investors can only partially observe the population. Herein, by incorporating social diversity in the Ultimatum game through heterogeneous graphs, we investigate the effects of several interference mechanisms which assume incomplete information and flexible standards of fairness. We quantify the role of diversity and show how it reduces the need for information gathering, allowing us to relax a strict, costly interference process. Furthermore, we find that the influence of certain individuals, expressed by different network centrality measures, can be exploited to further reduce spending if minimal fairness requirements are lowered. Our results indicate that diversity changes and opens up novel mechanisms available to institutions wishing to promote fairness. Overall, our analysis provides novel insights to guide institutional policies in socially diverse complex systems.

cs.MA↗

arXiv2022

Artificial Intelligence Development Races in Heterogeneous Settings

Regulation of advanced technologies such as Artificial Intelligence (AI) has become increasingly important, given the associated risks and apparent ethical issues. With the great benefits promised from being able to first supply such technologies, safety precautions and societal consequences might be ignored or shortchanged in exchange for speeding up the development, therefore engendering a racing narrative among the developers. Starting from a game-theoretical model describing an idealised technology race in a fully connected world of players, here we investigate how different interaction structures among race participants can alter collective choices and requirements for regulatory actions. Our findings indicate that, when participants portray a strong diversity in terms of connections and peer-influence (e.g., when scale-free networks shape interactions among parties), the conflicts that exist in homogeneous settings are significantly reduced, thereby lessening the need for regulatory actions. Furthermore, our results suggest that technology governance and regulation may profit from the world's patent heterogeneity and inequality among firms and nations, so as to enable the design and implementation of meticulous interventions on a minority of participants, which is capable of influencing an entire population towards an ethical and sustainable use of advanced technologies.

cs.AI↗

arXiv2021

Promoting Fair Proposers, Fair Responders or Both? Cost-Efficient Interference in the Spatial Ultimatum Game

Institutions and investors face the constant challenge of making accurate decisions and predictions regarding how best they should distribute their endowments. The problem of achieving an optimal outcome at minimal cost has been extensively studied and resolved using several heuristics. However, these works usually fail to address how an external party can target different types of fair behaviour or do not take into account how limited information can shape this complex interplay. Here, we consider the well-known Ultimatum game in a spatial setting and propose a hierarchy of interference mechanisms based on the amount of information available to an external decision-maker and desired standards of fairness. Our analysis reveals that monitoring the population at a macroscopic level requires more strict information gathering in order to obtain an optimal outcome and that local observations can mediate this requirement. Moreover, we identify the conditions which must be met for an individual to be eligible for investment in order to avoid unnecessary spending. We further explore the effects of varying mutation or behavioural exploration rates on the choice of investment strategy and total accumulated costs to the investor. Overall, our analysis provides new insights about efficient heuristics for cost-efficient promotion of fairness in societies. Finally, we discuss the differences between our findings and previous work done on the PD and present our suggestions for promoting fairness as an external decision-maker.

cs.MA↗

arXiv2020

Making an Example: Signalling Threat in the Evolution of Cooperation

Social punishment has been suggested as a key approach to ensuring high levels of cooperation and norm compliance in one-shot (i.e. non-repeated) interactions. However, it has been shown that it only works when punishment is highly cost-efficient. On the other hand, signalling retribution hearkens back to medieval sovereignty, insofar as the very word for gallows in French stems from the Latin word for power and serves as a grim symbol of the ruthlessness of high justice. Here we introduce the mechanism of signalling an act of punishment and a special type of defector emerges, one who can recognise this signal and avoid punishment by way of fear. We describe the analytical conditions under which threat signalling can maintain high levels of cooperation. Moreover, we perform extensive agent-based simulations so as to confirm and expand our understanding of the external factors that influence the success of social punishment. We show that our suggested mechanism catalyses cooperation, even when signalling is costly or when punishment would be impractical. We observe the preventive nature of advertising retributive acts and we contend that the resulting social prosperity is a desirable outcome in the contexts of AI and multi-agent systems. To conclude, we argue that fear acts as an effective stimulus to pro-social behaviour.

cs.GT↗

arXiv2019

Exogenous Rewards for Promoting Cooperation in Scale-Free Networks

The design of mechanisms that encourage pro-social behaviours in populations of self-regarding agents is recognised as a major theoretical challenge within several areas of social, life and engineering sciences. When interference from external parties is considered, several heuristics have been identified as capable of engineering a desired collective behaviour at a minimal cost. However, these studies neglect the diverse nature of contexts and social structures that characterise real-world populations. Here we analyse the impact of diversity by means of scale-free interaction networks with high and low levels of clustering, and test various interference mechanisms using simulations of agents facing a cooperative dilemma. Our results show that interference on scale-free networks is not trivial and that distinct levels of clustering react differently to each interference mechanism. As such, we argue that no tailored response fits all scale-free networks and present which mechanisms are more efficient at fostering cooperation in both types of networks. Finally, we discuss the pitfalls of considering reckless interference mechanisms.

cs.GT↗