arXiv subjects

Babak Heydari

Publications and source records attributed to Babak Heydari.

16 recordsLinked to original sources

arXiv2026

Adaptive Complementarity in Human-AI Systems: Architecture as a State-Shaping Choice

Human-AI interaction can improve current performance while changing the capabilities and relationships on which future performance depends. We develop adaptive complementarity, a framework for choosing interaction architecture with these state consequences in view. Access, information exposure, task allocation, timing, and communication can alter which arrangement will be valuable later; their settings can often be reset faster than the capabilities, search patterns, or conventions they create. Three mechanisms organize the argument: information exposure and collective search, delegation and capability evolution, and strategic interdependence and information governance. Their integration yields cross-mechanism implications, including conditions under which a loss of expertise heterogeneity increases the information differentiation required to preserve independent search. We distinguish strong human-AI complementarity from advantage over another workflow and from advantage over an evolving reference policy. A knowledge-coverage illustration shows how earlier workflows create expertise profiles that can reverse current workflow rankings even at equal human competence. It distinguishes current fit from investment in future learning and shows how a stable, forward-looking workflow can capture nearly all the baseline value available to a fully informed policy. The framework directs evaluation toward the states present interaction creates, their consequences for later architectural fit, and the conditions under which observing and responding to them is worthwhile.

cs.HC↗

arXiv2026

When Networks Substitute for Outcome Surveillance? A Substitution-Complementarity Framework for Behavioral Signals in Predictive Monitoring

Monitoring systems increasingly fuse dynamic behavioral data with outcome-based surveillance, raising a basic question: when does behavioral data carry predictive information that outcome history lacks? We study this using epidemic forecasting on mobility networks, asking whether mobility networks provide independent predictive signal beyond local outcome-based surveillance. We formalize this as a substitution-complementarity problem over directed, weighted mobility networks. Using a Frisch-Waugh-Lovell variance decomposition, our analytical framework derives domain-agnostic conditions under which network-topology features retain incremental explanatory power beyond autoregressive outcome histories. We instantiate the framework using town-level COVID-19 forecasting in Massachusetts (April 2020-April 2021), constructing mobility networks among 300+ towns from smartphone-derived origin-destination aggregates to extract centrality metrics. An agent-based model on synthetic networks confirms that the regime boundary arises from a generic interaction between macro-scale epidemic state and network topology, rather than dataset-specific artifacts. Prevalence-gated interactions between statewide incidence and network features yield large out-of-sample gains when primary surveillance is degraded (Predict-R2 increases from about 0.60 to 0.83-0.89) but only marginal lift when granular local histories are available (+0.5 percentage points). Gains concentrate during epidemic waves when behavioral responses shift network connectivity rapidly. Framed as a value-of-information problem, the substitution gain reflects the marginal value of behavioral data relative to primary-channel quality. This yields a transferable, cost-aware design rule: integrate topology-aware behavioral signals when primary surveillance is degraded or the network changes rapidly; otherwise, rely on autoregressive baselines.

physics.soc-ph↗

arXiv2026

Networked risk perception and behavioral bubbles: the case of a pandemic

Risk perception is typically modeled as an individual cognitive readout of objective hazard, yet during crises what people judge as risky is shaped by what their peers do. Using weekly mobility data from 313 Massachusetts municipalities over the first year of the COVID-19 pandemic and a pre-pandemic inter-town mobility network that fixes interaction structure before the shock, we estimate two-way fixed-effects panel regressions that separate local case response, inter-town behavioral spillover along the mobility network, and within-town inertia; the pre-shock network and a lagged peer signal address the standard reflection and endogenous-group concerns. Three findings emerge. First, inter-town behavioral spillovers are substantial and localize almost entirely within mobility-defined communities, with effectively no propagation across community boundaries, the empirical referent of behavioral bubbles. Second, the within-community spillover carries behavioral content beyond peer-town case information: when network-exposure-to-cases and network-exposure-to-behavior are raced, the behavioral channel survives and the case-exposure channel goes null. Third, a joint mobility-by-demographic decomposition shows the spillover requires both routine connection and demographic similarity. It concentrates where towns are connected and similar, and vanishes between similar towns that are not connected, ruling out a shared-conditions confound and pointing to an observational and normative channel rather than a purely informational one. These results recast risk perception as a networked phenomenon and identify mobility-defined communities, rather than administrative units, as the operative scale of behavioral response. The pattern should generalize wherever exposure is uncertain, evolving, and socially negotiated, including climate adaptation and financial contagion.

econ.EM↗

arXiv2026

The Architecture of Illusion: Network Opacity and Strategic Escalation

Standard models of bounded rationality typically assume agents either possess accurate knowledge of the population's reasoning abilities (Cognitive Hierarchy) or hold dogmatic, degenerate beliefs (Level-$k$). We introduce the ``Connected Minds'' model, which unifies these frameworks by integrating iterative reasoning with a parameterized network bias. We posit that agents do not observe the global population; rather, they observe a sample biased by their network position, governed by a locality parameter $p$ representing algorithmic ranking, social homophily, or information disclosure. We show that this parameter acts as a continuous bridge: the model collapses to the myopic Level-$k$ recursion as networks become opaque ($p \to 0$) and recovers the standard Cognitive Hierarchy model under full transparency ($p=1$). Theoretically, we establish that network opacity induces a \emph{Sophisticated Bias}, causing agents to systematically overestimate the cognitive depth of their opponents while preserving the log-concavity of belief distributions. This makes $p$ an actionable lever: a planner or platform can tune transparency, globally or by segment (a personalized $p_k$), to shape equilibrium behavior. From a mechanism design perspective, we derive the \emph{Escalation Principle}: in games of strategic complements, restricting information can maximize aggregate effort by trapping agents in echo chambers where they compete against hallucinated, high-sophistication peers. Conversely, we identify a \emph{Transparency Reversal} for coordination games, where maximizing network visibility is required to minimize variance and stabilize outcomes. Our results suggest that network topology functions as a cognitive zoom lens, determining whether agents behave as local imitators or global optimizers.

cs.GT↗

arXiv2026

Communication Enhances LLMs' Stability in Strategic Thinking

Large Language Models (LLMs) often exhibit pronounced context-dependent variability that undermines predictable multi-agent behavior in tasks requiring strategic thinking. Focusing on models that range from 7 to 9 billion parameters in size engaged in a ten-round repeated Prisoner's Dilemma, we evaluate whether short, costless pre-play messages emulating the cheap-talk paradigm affect strategic stability. Our analysis uses simulation-level bootstrap resampling and nonparametric inference to compare cooperation trajectories fitted with LOWESS regression across both the messaging and the no-messaging condition. We demonstrate consistent reductions in trajectory noise across a majority of the model-context pairings being studied. The stabilizing effect persists across multiple prompt variants and decoding regimes, though its magnitude depends on model choice and contextual framing, with models displaying higher baseline volatility gaining the most. While communication rarely produces harmful instability, we document a few context-specific exceptions and identify the limited domains in which communication harms stability. These findings position cheap-talk style communication as a low-cost, practical tool for improving the predictability and reliability of strategic behavior in multi-agent LLM systems.

cs.MA↗

arXiv2025

Integrated Design and Governance of Agentic AI Systems through Adaptive Information Modulation

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.

cs.AI↗

arXiv2024

Large Model Strategic Thinking, Small Model Efficiency: Transferring Theory of Mind in Large Language Models

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.

cs.CL↗

arXiv2024

Resource Governance in Networked Systems via Integrated Variational Autoencoders and Reinforcement Learning

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.

cs.LG↗

arXiv2024

Adaptive Network Intervention for Complex Systems: A Hierarchical Graph Reinforcement Learning Approach

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.

cs.LG↗

arXiv2024

Platform-Driven Collaboration Patterns: Structural Evolution Over Time and Scale

Within an increasingly digitalized organizational landscape, this research delves into the dynamics of decentralized collaboration, contrasting it with traditional collaboration models. An effective capturing of high-level collaborations (beyond direct massages) is introduced as the network construction methodology including both temporal and content dimensions of user collaborations - an Alternating Timed Interaction (ATI) metric as the first aspect, and a quantitative strategy of thematic similarity as the second aspect. This study validates three hypotheses that collectively underscore the complexities of digital team dynamics within sociotechnical systems: Firstly, it establishes the significant influence of problem context on team structures in work environments, emphasizing the need to consider the specific nature of tasks in analyzing collaborative dynamics. Secondly, the study reveals specific evolving patterns of team structures on digital platforms concerning team size and artifact maturity. Lastly, it identifies substantial differences in team structure patterns between digital platforms and traditional organizational settings, underscoring the unexplored nature of digital collaboration dynamics. The findings of this study are instrumental for organizations navigating the digital era, offering insights into effective knowledge sharing in the decentralized leadership of digital teams. By mapping out network structures and collaborative patterns, this study, with a focus on Wikipedia as a representative digital platform, paves the way for strategic interventions to optimize digital team dynamics and align them with broader organizational goals.

cs.SI↗

arXiv2023

Strategic Behavior of Large Language Models: Game Structure vs. Contextual Framing

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.

cs.GT↗

arXiv2016

Distributed Resource Management in Systems of Systems: An Architecture Perspective

This paper introduces a framework for studying the interactions of autonomous system components and the design of the connectivity structure in Systems of Systems (SoSs). This framework, which uses complex network models, is also used to study the connectivity structure's impact on resource management. We discuss resource sharing as a mechanism that adds a level of flexibility to distributed systems and describe the connectivity structures that enhance components' access to the resources available within the system. The framework introduced in this paper explicitly incorporates costs of connection and the benefits that are received by direct and indirect access to resources and provides measures of the optimality of connectivity structures. We discuss central and a distributed schemes that, respectively, represent systems in which a central planner determines the connectivity structure and systems in which distributed components are allowed to add and sever connections to improve their own resource access. Furthermore, we identify optimal connectivity structures for systems with various heterogeneity conditions.

cs.DC↗

arXiv2016

From Modular to Distributed Open Architectures: A Unified Decision Framework

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.

eess.SY↗

arXiv2016

An Incentive-Compatible Scheme for Electricity Cooperatives: An Axiomatic Approach

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.

cs.GT↗

arXiv2016

Distributed or Monolithic? A Computational Architecture Decision Framework

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.

cs.DC↗

arXiv2015

Efficient Network Structures with Separable Heterogeneous Connection Costs

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.

econ.GN↗