Babak Heydari

Babak Heydari, Mohsen Mosleh, Kia Dalili

We introduce a heterogeneous connection model for network formation to capture the effect of cost heterogeneity on the structure of efficient networks. In the proposed model, connection costs are assumed to be separable, which means the total connection cost for each agent is uniquely proportional to its degree. For these sets of networks, we provide the analytical solution for the efficient network and discuss stability impli- cations. We show that the efficient network exhibits a core-periphery structure, and for a given density, we find a lower bound for clustering coefficient of the efficient network.

Nunzio Lorè, Babak Heydari

This paper investigates the strategic decision-making capabilities of three Large Language Models (LLMs): GPT-3.5, GPT-4, and LLaMa-2, within the framework of game theory. Utilizing four canonical two-player games -- Prisoner's Dilemma, Stag Hunt, Snowdrift, and Prisoner's Delight -- we explore how these models navigate social dilemmas, situations where players can either cooperate for a collective benefit or defect for individual gain. Crucially, we extend our analysis to examine the role of contextual framing, such as diplomatic relations or casual friendships, in shaping the models' decisions. Our findings reveal a complex landscape: while GPT-3.5 is highly sensitive to contextual framing, it shows limited ability to engage in abstract strategic reasoning. Both GPT-4 and LLaMa-2 adjust their strategies based on game structure and context, but LLaMa-2 exhibits a more nuanced understanding of the games' underlying mechanics. These results highlight the current limitations and varied proficiencies of LLMs in strategic decision-making, cautioning against their unqualified use in tasks requiring complex strategic reasoning.

Nunzio Lore, Sepehr Ilami, Babak Heydari

As the performance of larger, newer Large Language Models continues to improve for strategic Theory of Mind (ToM) tasks, the demand for these state-of-the-art models increases commensurately. However, their deployment is costly both in terms of processing power and time. In this paper, we investigate the feasibility of creating smaller, highly-performing specialized algorithms by way of fine-tuning. To do this, we first present a large pre-trained model with 20 unique scenarios that combine different social contexts with games of varying social dilemmas, record its answers, and use them for Q&A fine-tuning on a smaller model of the same family. Our focus is on in-context game-theoretic decision-making, the same domain within which human interaction occurs and that requires both a theory of mind (or a semblance thereof) and an understanding of social dynamics. The smaller model is therefore trained not just on the answers provided, but also on the motivations provided by the larger model, which should contain advice and guidelines to navigate both strategic dilemmas and social cues. We find that the fine-tuned smaller language model consistently bridged the gap in performance between the smaller pre-trained version of the model and its larger relative and that its improvements extended in areas and contexts beyond the ones provided in the training examples, including on out-of-sample scenarios that include completely different game structures. On average for all games, through fine-tuning, the smaller model showed a 46% improvement measured as alignment towards the behavior of the larger model, with 100% representing indistinguishable behavior. When presented with out-of-sample social contexts and games, the fine-tuned model still displays remarkable levels of alignment, reaching an improvement of 18% and 28% respectively.

Qiliang Chen, Sepehr Ilami, Nunzio Lore et al.

Modern engineered systems increasingly involve complex sociotechnical environments where multiple agents, including humans and the emerging paradigm of agentic AI powered by large language models, must navigate social dilemmas that pit individual interests against collective welfare. As engineered systems evolve toward multi-agent architectures with autonomous LLM-based agents, traditional governance approaches using static rules or fixed network structures fail to address the dynamic uncertainties inherent in real-world operations. This paper presents a novel framework that integrates adaptive governance mechanisms directly into the design of sociotechnical systems through a unique separation of agent interaction networks from information flow networks. We introduce a system comprising strategic LLM-based system agents that engage in repeated interactions and a reinforcement learning-based governing agent that dynamically modulates information transparency. Unlike conventional approaches that require direct structural interventions or payoff modifications, our framework preserves agent autonomy while promoting cooperation through adaptive information governance. The governing agent learns to strategically adjust information disclosure at each timestep, determining what contextual or historical information each system agent can access. Experimental results demonstrate that this RL-based governance significantly enhances cooperation compared to static information-sharing baselines.

Qiliang Chen, Babak Heydari

Effective governance and steering of behavior in complex multi-agent systems (MAS) are essential for managing system-wide outcomes, particularly in environments where interactions are structured by dynamic networks. In many applications, the goal is to promote pro-social behavior among agents, where network structure plays a pivotal role in shaping these interactions. This paper introduces a Hierarchical Graph Reinforcement Learning (HGRL) framework that governs such systems through targeted interventions in the network structure. Operating within the constraints of limited managerial authority, the HGRL framework demonstrates superior performance across a range of environmental conditions, outperforming established baseline methods. Our findings highlight the critical influence of agent-to-agent learning (social learning) on system behavior: under low social learning, the HGRL manager preserves cooperation, forming robust core-periphery networks dominated by cooperators. In contrast, high social learning accelerates defection, leading to sparser, chain-like networks. Additionally, the study underscores the importance of the system manager's authority level in preventing system-wide failures, such as agent rebellion or collapse, positioning HGRL as a powerful tool for dynamic network-based governance.

Qiliang Chen, Babak Heydari

We introduce a framework that integrates variational autoencoders (VAE) with reinforcement learning (RL) to balance system performance and resource usage in multi-agent systems by dynamically adjusting network structures over time. A key innovation of this method is its capability to handle the vast action space of the network structure. This is achieved by combining Variational Auto-Encoder and Deep Reinforcement Learning to control the latent space encoded from the network structures. The proposed method, evaluated on the modified OpenAI particle environment under various scenarios, not only demonstrates superior performance compared to baselines but also reveals interesting strategies and insights through the learned behaviors.

Mohsen Mosleh, Kia Dalili, Babak Heydari

Distributed architectures have become ubiquitous in many complex technical and socio-technical systems because of their role in improving uncertainty management, accommodating multiple stakeholders, and increasing scalability and evolvability. This departure from monolithic architectures provides a system with more flexibility and robustness in response to uncertainties that it may confront during its lifetime. Distributed architecture does not provide benefits only, as it can increase cost and complexity of the system and result in potential instabilities. The mechanisms behind this trade-off, however, are analogous to those of the widely-studied transition from integrated to modular architectures. In this paper, we use a conceptual decision framework that unifies modularity and distributed architecture on a five-stage systems architecture spectrum. We add an extensive computational layer to the framework and explain how this can enhance decision making about the level of modularity of the architecture. We then apply it to a simplified demonstration of the Defense Advanced Research Projects Agency (DARPA) fractionated satellite program. Through simulation, we calculate the net value that is gained (or lost) by migrating from a monolithic architecture to a distributed architecture and show how this value changes as a function of uncertainties in the environment and various system parameters. Additionally, we use Value at Risk as a measure for the risk of losing the value of distributed architecture, given its inherent uncertainty.

Babak Heydari, Mohsen Mosleh, Kia Dalili

This paper introduces a conceptual, yet quantifiable, architecture framework by extending the notion of system modularity in its broadest sense. Acknowledging that modularity is not a binary feature and comes in various types and levels, the proposed framework introduces higher levels of modularity that naturally incorporate decentralized architecture on the one hand and autonomy in agents and subsystems on the other. This makes the framework suitable for modularity decisions in Systems of Systems and for analyzing the impact of modularity on broader surrounding ecosystems. The stages of modularity in the proposed framework are naturally aligned with the level of variations and uncertainty in the system and its environment, a relationship that is central to the benefits of modularity. The conceptual framework is complemented with a decision layer that makes it suitable to be used as a computational architecture decision tool to determine the appropriate stage and level of modularity of a system, for a given profile of variations and uncertainties in its environment. We further argue that the fundamental systemic driving forces and trade-offs of moving from monolithic to distributed architecture are essentially similar to those for moving from integral to modular architectures. The spectrum, in conjunction with the decision layer, could guide system architects when selecting appropriate parameters and building a system-specific computational tool from a combination of existing tools and techniques. To demonstrate the applicability of the framework, a case for fractionated satellite systems based on a simplified demo of the DARPA F6 program is presented.

Abbas Ehsanfar, Babak Heydari

This paper introduces a new scheme for autonomous electricity cooperatives, called predictive cooperative (PCP), which aggregates commercial and residential electricity consumers and participates in the electricity market on behalf of its members. An axiomatic approach is proposed to calculate the day-ahead bid and to disaggregate the collective cost among participating consumers. The resulting formulation is shown to keep the members incentivized to both participate in the cooperative and remain truthful in reporting their expected loads. The scheme is implemented using PJM (world's largest wholesale electricity market) real-time and day-ahead price data for 2015 and a collection of residential and commercial load profiles. The model performance of this framework is compared to that of real-time pricing (RTP) scheme, in which wholesale market prices are directly applied to individual consumers. The results show truthful load announcement by consumers, reduction in electricity price variation for all consumers, and comparative benefits for participants.