Searcharxiv⌕ Search

arXiv subjects

The Anh Han

Publications and source records attributed to The Anh Han.

At least 19 recordsLinked to original sources

Equilibrium Statistics and Stability in Random Two-Population and Three-Population Evolutionary Games

Multi-population matrix evolutionary games provide a framework for studying adaptation and strategic interactions among heterogeneous agents. When payoffs are uncertain, however, analysing a specified game does not reveal how frequently different evolutionary outcomes occur or how their probabilities depend on modelling assumptions. We study two- and three-population games with two strategies per population and both within- and between-population pairwise interactions, with payoffs fixed during each evolutionary trajectory. For two populations, we derive equilibrium-existence probabilities and analytical stability results for generic games and three structured classes: diversity, exclusive, and avoidance games. For generic two-population games, independent Gaussian sampling of payoff entries and of replicator coefficients produces different equilibrium statistics. Interaction structure further distinguishes coexistence from attraction: diversity and exclusive games share the same interior-existence probability, but only exclusive games admit asymptotically stable interior equilibria. Avoidance games admit transversely attracting equilibrium families without locally asymptotically stable individual points. For generic three-population games under independent payoff sampling, we obtain existence probabilities for all equilibrium types and joint existence-and-stability probabilities for boundary equilibria. Monte Carlo simulations support the analytical predictions and quantify multistability, while phase portraits illustrate initial-condition dependence. Under the same Gaussian payoff-sampling protocol, simulations show a lower frequency of fully mixed equilibria but a higher frequency of multistability for three populations than for two.

cs.GT↗

From Apology to Action: Apologies, Compensation, and Cooperation in LLM Agents

Large language models (LLMs) can make decisions that affect other agents, but what happens after a harmful or unsuccessful interaction remains poorly understood. We investigate whether apologies by LLM agents are associated with subsequent cooperative behaviour, using controlled Prisoner's Dilemma experiments with four commercial models (Claude Opus 4.8, GPT-5.5, Gemini 3.1 Pro, and Mistral Large 3). Across payoff conditions, we examine when agents apologise, the reasons they provide, and the actions that follow. We also examine how access to one round of interaction history affects behaviour and, in a second experiment, whether and how agents offer compensation alongside their apologies. Apology behaviour differed substantially across models and preceding interaction outcomes, and verbal expressions of cooperation did not always align with subsequent actions. Notably, Claude Opus 4.8 apologised even after mutual cooperation, while Mistral Large 3 apologised after being exploited but continued to defect even when its opponent cooperated. After unilateral defection, positively compensated apologies from GPT-5.5 and Gemini 3.1 Pro were followed by mutual cooperation, unlike those from Claude and Mistral. Our findings suggest that apologies, compensation, and strategic behaviour are distinct: conciliatory messages may precede continued defection, while costly apologies may go unanswered. This has important implications for the study of machine behaviour and human-AI interactions, as verbal signals alone may not reliably reflect an AI system's subsequent actions.

cs.GT↗

Payoff scaling shapes cooperation in LLM agents across languages

Large language models (LLMs) are increasingly deployed as autonomous agents that negotiate, coordinate, and make decisions on behalf of human users. Understanding how they cooperate is therefore important for AI governance and machine behaviour research. We examine two factors: payoff magnitude and interaction language. Classical game theory predicts that multiplying all payoffs by a positive constant should not change behaviour because the underlying strategic incentives remain unchanged. We test this prediction using five widely adopted commercial LLMs playing an iterated prisoner's dilemma across ten payoff scales and five languages (English, French, Vietnamese, Chinese and Arabic). Contrary to theoretical expectations, changing only the numerical scale of payoffs substantially alters cooperation. Models respond differently, often in opposite directions, meaning that averages across models can conceal important behavioural heterogeneity. Sensitivity to payoff scale also depends strongly on prompt language. Moreover, payoff scale modifies the effects of persona instructions: at sub-unit stakes, where no payoff shown exceeds 1, all five models cooperate more under a selfish than a cooperative persona, whereas Claude and Gemini reverse this pattern at larger scales. These findings show that cooperation measures depend critically on payoff scale and language and should not be treated as fixed model traits.

cs.AI↗

Cooperation Without Adaptation: LLM Agents in a Collective-Risk Dilemma

Language-model agents are increasingly deployed to act on behalf of people in settings where individual decisions shape shared outcomes. We examine whether five production models adapt their contributions to changing risks and partner behaviour, or instead follow a relatively fixed strategy. In a collective-risk dilemma game (CRG), six players contribute to a shared pool over ten rounds; if the pool falls short of its target, a catastrophe may destroy their remaining resources. Four models contributed approximately an equal share at every positive risk level, and four of the five also contributed when risk was zero, even though contributing could not improve their payoff. Explicitly stating that only the agent's own payoff mattered reduced zero-risk contributions for most models, while a more neutral prompt did not. Several models correctly identified which action offered the higher expected payoff at different risk levels, yet their contributions changed little. Against fixed partners, no model consistently chose the payoff-maximising response, and in mixed-model groups, a single agent's shortfall in the final round could cause an otherwise successful group to fail. Payoff-based selection also depended on population composition: in a single six-agent group, it favoured the model that contributed least and reduced group success, whereas in larger, randomly mixed populations, it favoured an exact fair-share model at moderate and high risk. These findings show that cooperative self-play alone is not evidence of strategic adaptability. Consistent with a machine-behaviour approach, evaluations of agents in multi-agent systems should test how they respond to incentives, partner actions, and population composition.

cs.GT↗

Network Topology Shapes AI Intervention Effectiveness on Deception: Truth-Telling vs. Investigative Agents

Deploying AI agents to combat dishonest communication is an intuitive response to deception in hybrid human-AI societies. However, the efficacy of such interventions in realistic networked settings remains unclear. We study this problem using an evolutionary game-theoretic model of the Deceiver's Game by extending it to structured networks, where agents can adopt deception, truth-telling, and investigation strategies. We introduce committed AI agents (zealots) fixed to either truth-telling or investigative strategies and conduct agent-based simulations across three network topologies. Our key findings are: (1) passive committed truth-telling agents can amplify adaptive deception by creating exploitable honest partners, whereas investigative agents increase adaptive truth-telling in the oscillatory regime; (2) intervention effects are non-monotonic in deployment density because committed agents reshape rather than simply suppress the underlying oscillatory dynamics; and (3) response peaks depend on topology, with sampled scale-free populations showing sharp low-density responses and fully connected populations requiring larger committed fractions. Overall, the results highlight the need to distinguish passive truth-telling from active investigation when using committed agents to influence networked deception dynamics.

cs.GT↗

When Numbers Start Talking: Numerical Signalling and Strategic Behaviour Among LLMs

Large language model (LLM)-based agents increasingly operate in multi-agent systems (MAS) characterised by strategic interaction. However, little is known about whether, and to what extent, different types of messages affect the outcomes of strategic games. By investigating AI agents based on four popular LLMs, playing four games with different cooperation equilibria, we study whether messages of different kinds (natural language, numerical signals, or random sequences) significantly modify the levels of cooperation in each game, also depending on the agents' assigned personalities. We observe that structured messages alter the final payoffs for most games and LLMs, but without a predictable pattern; this challenges the assumption that AI agents can converge to stable equilibria regardless of additional capabilities. Moreover, we observe that agent-generated numerical messages depart from randomness, most strongly and consistently when agents are explicitly instructed to communicate; however, they introduce an additional interpretability challenge, as their symbol distributions are mostly associated with the payoff structure and typically become more concentrated with repetition, but are overall difficult for humans to interpret. Monitoring for coordination of AI agents through restricted channels should thus prioritise message-level fingerprints, which generalise across models, over behavioural decisions, which do not.

cs.AI↗

Complete strategy spaces reveal hidden pathways to cooperation

Understanding how cooperation emerges and persists is a central challenge in evolutionary game theory. Existing models often rely on restricted, hand-picked strategy sets, which can overlook critical behavioural pathways. A recent four-strategy framework showed that cheap talk can promote cooperation through local interactions, yet it remained unclear whether modelled strategies might alter these conclusions. Here, we extend this framework to the complete set of eight strategies that naturally arise from communication and decision-making rules. We show that incorporating the full strategy space dramatically changes the evolutionary landscape. Cooperation becomes both more robust and more versatile, driven by novel pathways absent in the restricted model. In particular, we uncover a previously overlooked mechanism in which suspicious cooperation catalyses a cyclic dynamic that sustains cooperation. Conversely, the assumed role of strategic defection in the biased model is fragile, acting mainly as a spoiler rather than a genuine evolutionary attractor. The complete model further reveals a rich spectrum of long-term behaviours, including stable coexistence among up to seven strategies and time-varying patterns of partial coexistence. These results demonstrate that the full strategy space unlocks hidden routes to cooperative behaviour and highlight the importance of comprehensive modelling when explaining the emergence of cooperation.

q-bio.PE↗

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↗

Co-evolution of social reward and punishment under institutional interventions

We investigate how peer and institutional incentives jointly shape the evolution of cooperation, social welfare, and enforcement efficiency in social dilemmas. In a Prisoners Dilemma with four strategies, unconditional cooperators (C), defectors (D), social punishers (SP), and social rewarders (SR), we allow decentralised peer incentives and centralised institutional incentives to act simultaneously, with the institution able to reward or punish any subset of strategies. In infinite well-mixed populations, we analyse the resulting four-strategy replicator dynamics, and in structured populations we use agent-based simulations on square lattices to study spatial effects and network reciprocity. Intervention schemes are evaluated by equilibrium states and evolutionary flow for infinite well-mixed populations, by cooperation levels and social welfare for structured populations, defined as aggregate population payoff net of institutional cost. We find that peer punishment most strongly promotes cooperation, whereas peer reward is more beneficial for social welfare. Institutionally rewarding peer incentive strategies substantially improves both cooperation and welfare, while subsidising unconditional cooperators has little impact. Under institutional punishment, directly penalising defectors is the only consistently effective policy; punishing peer incentive strategies dismantles decentralised incentives, reduces cooperation, and harms social welfare, showing that maximising cooperation does not necessarily optimise overall societal benefit. Our findings provide design principles for institutions seeking to balance cooperation promotion with welfare maximisation.

cs.AI↗

Humans Are More Diverse: Frontier LLMs Show Extreme Policies in Idealised AI Development Races

An AI development race creates a multi-agent safety dilemma. Each company can develop slowly and safely, or move faster while taking a risk that may remove its final reward. We use this repeated game to study strategic safety behaviour among large language model (LLM) agents in races with two to five players. However, a valid action does not show that an agent understands the game. We therefore place an audit gate before behavioural interpretation. We first verify the game engine, then test rule recall, state tracking, payoff calculation, and stability under different but equivalent task descriptions. We then compare LLM action sequences with an evolutionary game-theory benchmark and published human data, and explore differences across models, risk conditions, personas, and two- to five-player races. The audit shows that strong rule recall can coexist with weak state tracking and expected-payoff calculation. Providing verified arithmetic and changing the response representation can also change later actions, even when the game rules stay fixed. Across seven tested model endpoints, aggregate rates hide large differences in action sequences, responses to opponents, and responses to race position. Patterns across the tested three- to five-player races are also model-specific rather than a single effect of adding competitors. These results show why multi-agent AI-race simulations need validity checks and trajectory-level analysis before their outputs are described as strategic, human-like, or safety-aware. Our findings are exploratory and apply only to the tested models, prompts, and decoding settings.

cs.AI↗

Reputation-driven Cooperation in Lattice-based Decentralized Federated Learning through Evolutionary Game Theory

Decentralized Federated Learning (DFL) has emerged as an optimal privacy-preserving solution; however, it remains vulnerable to opportunistic behaviors due to the absence of a central coordinator. While Evolutionary Game Theory (EGT) serves as a powerful framework for analyzing such behaviors, existing studies often assume that agents possess perfect rationality and maintain static strategies. To address these limitations, this paper proposes a novel EGT framework designed to analyze strategic evolution and enhance overall system performance. The primary contributions of this work are threefold: First, we model peer-to-peer (P2P) interactions on a lattice network structure under the assumption of bounded rationality. Second, we formulate a comprehensive payoff matrix incorporating training costs, communication overhead, and cooperative rewards, while tailoring a strategy update rule that captures spatial propagation dynamics. Third, we integrate a reputation-based reward-and-punishment mechanism to effectively deter free-riding behaviors. Simulation results demonstrate that the framework significantly outperforms the baseline. Specifically, it increases average accuracy from approximately 70% to 82%, elevates cooperation frequency to approach 100% (compared to below 5% in the baseline), and drops accuracy variance from around 0.40 to 0.002, thereby accelerating uniform convergence and ensuring system stability.

cs.AI↗

Network Reciprocity Shapes Evolutionary Cybersecurity Dynamics

AI-assisted cybersecurity systems are characterised by continuous adaptation between attackers and defenders, making evolutionary game theory a natural framework for studying their long-term behaviour. However, existing evolutionary cybersecurity models have primarily focused on homogeneous interactions, providing limited understanding of how population structure influences cyber attack-defence dynamics. In this paper, we develop a mixed-role evolutionary game in which adaptive cyber agents can exhibit both offensive and defensive behaviours, and investigate its dynamics in well-mixed and structured populations. The proposed framework combines stochastic evolutionary analysis with large-scale agent-based simulations to examine how interaction structure shapes long-run strategic behaviour. Our results reveal a fundamental difference between global and local interactions. While well-mixed populations exhibit broad coexistence between attacking and defensive strategies, structured populations generate well-defined evolutionary regimes in which secure defensive behaviour becomes dominant over a much larger region of the parameter space. Spatial analysis further shows that neighbouring defenders naturally form resilient clusters that suppress persistent attacks through network reciprocity. These findings demonstrate that interaction structure is a fundamental determinant of AI-assisted cybersecurity evolution and suggest that organising defensive agents through local networked interactions can substantially improve long-term cyber resilience without requiring additional defensive incentives.

cs.GT↗

Falling Behind Drives Unsafe Development in an Idealised AI Race Experiment

Technological races create tension between speed and safety: actors may gain by moving faster than competitors, even when risky development is harmful. This is prominent in debates about artificial intelligence (AI), where competitive pressure is often argued to incentivise riskier, less safety-conscious development. We study this using a framed behavioural experiment based on an idealised AI race, in which paired participants repeatedly chose between Safe and Unsafe development under an uncertain time horizon. Unsafe development gave faster progress and higher immediate payoffs but accumulated private risk up to a treatment-specific maximum of 10\%, 60\%, or 90\%; the race's competitive structure was held constant, and only this maximum risk varied. Neither the pre-registered comparison between risk levels nor the role of elicited risk preferences was supported by the data. Instead, exploratory analyses motivated by the task's repeated structure show that Unsafe behaviour is shaped less by risk preferences than by the evolving strategic state of the race: participants are more likely to choose Unsafe after their opponent does so, being ahead reduces Unsafe play while falling behind increases it, and first-round choices predict later behaviour. To interpret these effects we introduce a reduced evolutionary model with four strategies -- Always Safe, Always Unsafe, Conditionally Safe, and Conditionally Antisocial Safe -- which reproduces the treatment effect and shows how conditional Unsafe behaviour can be favoured by competitive race dynamics. Together, the experiment and model show that unsafe development can emerge from early behavioural momentum, opponent behaviour, and fear of falling behind, rather than from risk preferences alone, suggesting policy should focus on reducing competitive pressure and promoting cooperation in AI development rather than only individual risk.

cs.AI↗

Prioritization of Risks from Artificial Intelligence: A Delphi Study of 272 International Experts

Artificial intelligence poses many risks, ranging from familiar present-day harms to unprecedented and potentially catastrophic ones. Effective risk management requires prioritization: we must understand which risks are most severe, who is most vulnerable, and who is most responsible for addressing them. We report results from a three-round Delphi study conducted late 2025 with 272 international AI experts. Experts rated 24 AI risks on harm probability and severity, sector and actor vulnerability, actor responsibility, and overall concern. Experts estimated the five most severe harms in the next 5 years were likely to come from dangerous capabilities, competitive dynamics, weapons & cyberattacks (including CBRNE), power centralization, and false information. In a business-as-usual scenario, experts judged 18 of 24 risks as having a more than 10% probability of catastrophic outcomes (e.g., more than 1 million deaths or more than USD 100B in financial loss) in the next 5 years (2025-2030). In a scenario where pragmatic mitigations are implemented, experts still judged five risks as having a more than 10% probability of catastrophic outcomes: dangerous capabilities, weapons & cyberattacks, environmental harm, inequality & unemployment, and power centralization. All 24 risks were judged as being more than 5% likely to cause catastrophic outcomes. AI users and the general public were judged the most vulnerable to these risks, but experts assigned the highest responsibility for addressing them to general-purpose AI developers and governance actors (including governments, regulators, and standards bodies). Across most risks, experts identified information, finance, and national security as the most vulnerable sectors. These findings can guide AI risk prioritization and clarify expert expectations about who should bear responsibility for mitigation.

cs.CY↗

Social welfare optimisation under institutional reward and punishment

Institutional incentives are widely used to promote cooperation among autonomous, self-regarding agents, from human societies to multi-agent and AI systems. Existing work typically treats incentive design as a bi-objective problem: minimise institutional cost while achieving a high long-run frequency of cooperation. Whether such schemes also maximise social welfare - total population payoff net of institutional expenditure - has remained largely unexplored. We develop a welfare-centric framework for institutional incentives in finite, well-mixed populations playing a social dilemma (Donation Game and Public Goods Game), considering both rewards for cooperators and punishments for defectors. For each mechanism, we derive explicit expressions for expected social welfare and characterise how it depends on incentive efficiency and selection intensity. Analytically, we identify parameter regimes where social welfare has a single optimal incentive level and regimes with qualitative phase transitions, in which welfare becomes non-monotonic with multiple local optima. We prove that any welfare-maximising incentive is either zero or concentrated around a simple closed-form target, and we provide an efficient algorithm to compute these optima. Comparing reward and punishment, we further derive close-formed conditions under which reward outperform punishment in terms of social welfare for any given budget. Overall, our results reveal a systematic gap between incentives optimised for cost or cooperation frequency and those that maximise welfare.

cs.GT↗

Training-Free Cultural Alignment of Large Language Models via Persona Disagreement

Large language models increasingly mediate decisions that turn on moral judgement, yet a growing body of evidence shows that their implicit preferences are not culturally neutral. Existing cultural alignment methods either require per-country preference data and fine-tuning budgets or assume white-box access to model internals that commercial APIs do not expose. In this work, we focus on this realistic black-box, public-data-only regime and observe that within-country sociodemographic disagreement, not consensus, is the primary steering signal. We introduce DISCA (Disagreement-Informed Steering for Cultural Alignment), an inference-time method that instantiates each country as a panel of World-Values-Survey-grounded persona agents and converts their disagreement into a bounded, loss-averse logit correction. Across 20 countries and 7 open-weight backbones (2B--70B), DISCA reduces cultural misalignment on MultiTP by 10--24% on the six backbones >=3.8B, and 2--7% on open-ended scenarios, without changing any weights. Our results suggest that inference-time calibration is a scalable alternative to fine-tuning for serving the long tail of global moral preferences.

cs.CL↗

Strategic commitments shape collective cybersecurity under AI inequality

The growing integration of AI into cybersecurity is reshaping the balance between attackers and defenders. When access to advanced AI-enabled defence tools is uneven, resource-limited defenders may be unable to adopt effective protection, creating persistent system vulnerabilities. We study the impact of differential AI access using an evolutionary game-theoretic model in a finite population. We first show that when high-capability defence is costly, the population is driven toward low-cost, weak-defence behaviour, sustaining attacks and weakening long-run security. To address this problem, we introduce differential access to AI defence tools by allowing defenders to choose between low- and high-capability protection based on their resources. We then examine the role of a small group of committed defenders who always adopt strong defence and influence others through social learning. Although commitment increases the prevalence of strong defence, it alone cannot stabilise secure outcomes due to high defence costs. We therefore incorporate a targeted subsidy to remove the cost disadvantage from committed defenders. Our analysis shows that subsidised commitment significantly increases strong defence adoption, suppresses successful attacks, and improves overall system resilience. Simulations across a broad parameter space confirm that subsidies consistently outperform commitment alone. In addition, social-welfare analysis shows improved defender outcomes while keeping attacker gains low. These findings suggest that targeted support for key defenders can be an effective mechanism for stabilising cybersecurity in AI-driven environments and provide a theoretical bridge between cybersecurity policy, AI governance, and strategic allocation of defensive AI capabilities.

cs.AI↗

Mathematical Modelling of Ethical AI Use in Higher Education: A Coordination Game Framework for Future-Facing Learning

The rapid uptake of generative artificial intelligence (AI) in higher education is reshaping assessment practices and intensifying concerns around academic integrity, fairness, and learning quality. While institutional responses increasingly emphasise policy guidance and ethical principles, there remains limited formal understanding of how collective norms of responsible or opportunistic AI use emerge and stabilise within student cohorts. This paper reframes student AI use in assessment as a coordination problem shaped by peer expectations and assessment design rather than individual compliance alone. We develop a coordination-based evolutionary game-theoretic framework that captures learning value, effort, perceived fairness, and transparency, with institutional AI governance modelled implicitly through reflective assessment incentives. We use analytical results and finite-population simulations to reveal threshold-driven behavioural transitions in student AI use: small, well-calibrated changes in reflective assessment incentives can trigger rapid shifts towards responsible, learning-oriented AI-use norms, whereas weak or misaligned incentives allow opportunistic practices to persist. These non-linear dynamics explain why policy statements alone often fail to change behaviour, while modest assessment redesigns can have disproportionate effects. By providing a mechanism-level account of how assessment structures shape collective AI-use practices, this work offers higher education institutions an analytically grounded tool for Future Facing Learning, supporting proportionate, pedagogy-led AI governance without reliance on surveillance or punitive enforcement.

cs.CY↗