Agent-Based Model 研究方法的研究历程

… Agent-based modeling is a powerful technique that allows modeling social phenomena ab-initio or from first principles. In this paper, we review the history of agent-based models and …

… The scientist constructing an agent-based model has to know a lot about the empirically observed agents that shall be described by the ABM. Contrary to most of mainstream economic …

… The term Agent-Based Modeling (ABM) refers to a class of modeling methods designed for the study of systems whose dynamics are driven by successive interactions among …

Agent-based modeling (ABM) is a novel computational methodology for representing the behavior of individuals in order to study social phenomena. Its use is rapidly growing in many fields. We review ABM in economics and finance and highlight how it can be used to relax conventional assumptions in standard economic models. ABM has enriched our understanding of markets, industrial organization, labor, macro, development, public policy, and environmental economics. In financial markets, substantial accomplishments include understanding clustered volatility, market impact, systemic risk, and housing markets. We present a vision for how ABMs might be used in the future to build more realistic models of the economy and review some of hurdles that must be overcome to achieve this. (JEL C63, D00, E00, G00)

… agent-based … agent-based modeling by describing the foundations of ABMS, discussing some illustrative applications, and addressing toolkits and methods for developing agent-based …

Book detailsUri Wilensky and William Rand An Introduction to Agent-Based Modeling; Modeling Natural, Social, and Engineered Complex Systems with NetLogo; The MIT Press, Cambridge, Massachusetts London, England (2015), 504 pages, E-book ISBN: 9780262328111, Hard-cover ISBN: 9780262731898.

… and simulation (ABMS) is a new approach to modeling systems comprised of autonomous, … of agent-based applications in a variety of fields. Applications range from modeling agent …

All basic processes of ecological populations involve decisions; when and where to move, when and what to eat, and whether to fight or flee. Yet decisions and the underlying principles of decision-making have been difficult to integrate into the classical population-level models of ecology. Certainly, there is a long history of modeling individuals’ searching behavior, diet selection, or conflict dynamics within social interactions. When all individuals are given certain simple rules to govern their decision-making processes, the resultant population–level models have yielded important generalizations and theory. But it is also recognized that such models do not represent the way real individuals decide on actions. Factors that influence a decision include the organism’s environment with its dynamic rewards and risks, the complex internal state of the organism, and its imperfect knowledge of the environment. In the case of animals, it may also involve complex social factors, and experience and learning, which vary among individuals. The way that all factors are weighed and processed to lead to decisions is a major area of behavioral theory. While classic population-level modeling is limited in its ability to integrate decision-making in its actual complexity, the development of individual- or agent-based models (IBM/ABMs) (we use ABM throughout to designate both ‘agent-based modeling’ and an ‘agent-based model’) has opened the possibility of describing the way that decisions are made, and their effects, in minute detail. Over the years, these models have increased in size and complexity. Current ABMs can simulate thousands of individuals in realistic environments, and with highly detailed internal physiology, perception and ability to process the perceptions and make decisions based on those and their internal states. The implementation of decision-making in ABMs ranges from fairly simple to highly complex; the process of an individual deciding on an action can occur through the use of logical and simple (if-then) rules to more sophisticated neural networks and genetic algorithms. The purpose of this paper is to give an overview of the ways in which decisions are integrated into a variety of ABMs and to give a prospectus on the future of modeling of decisions in ABMs.

… agent-based modeling, the use of simulation methods is so ubiquitous that “agent-based model” and “agent-based computational model” … Agent-based simulations have a number of …

… an agent-based model are given, along with a discussion of what constitutes an agent-based model. … For example, via the GUI of the model we are able to track the simulation history as …

Agent-based modeling (ABM) is an emerging modeling approach. In the past two decades, agent-based models have been increasingly adapted by social scientists, especially scientists in urban and geospatial studies, as an effective paradigm for framing the underlying problems of complex and dynamic processes. As a result, the literature of ABM research is growing rapidly, covering a diverse range of topics. This paper presents a systematic literature review of ABM research, and discusses both theoretical issues such as ABM definition and architecture, and practical issues such as ABM applications and development platforms. A comprehensive and up-to-date bibliography is presented. & 2012 Higher Education Press Limited Company. Production and hosting by Elsevier B.V. All rights reserved.

This essay discusses agent-based modeling (ABM) and its potential as a technique for studying history, including literary history. How can a computer simulation tell us anything about the past? This essay has three distinct goals. The first is simply to introduce agent-based modeling as a computational practice to an audience of digital humanists, for whom it remains largely unfamiliar despite signs of increasing interest. Second, to introduce one possible application for social simulation by comparing it to conventional, print-based models of the history of book publishing. Third, and most importantly, I’ll sketch out a theory and preliminary method for incorporating social simulation into an on-going program of humanities research.

… evidence for the mechanisms on which the agent-based model is based. The transfer of … There may nevertheless be a common theory explaining both system behaviors, and history-…

… There exists a range of different approaches to modeling under the umbrella of agent-based modeling. Like game-theoretic models, agents in computational models often assume an …

… emerge from the model's mechanistic representation of key processes vs. being imposed on the model … an important reason why the individual-based approach to ecological modelling …

From zebra to starlings, herring and even tadpoles, many creatures move in an organized group. The emergent behaviour arises from simple underlying movement rules, but the evolutionary pressure which favours these rules has not been conclusively identified. Various explanations exist for the advantage to the individual of group formation: reduction of predation risk; increased foraging efficiency or reproductive success. Here, we adopt an individual-based model for group formation and subject it to simulated predation and foraging; the haploid individuals evolve via a genetic algorithm based on their relative success under such pressure. Our work suggests that flock or herd formation is likely to be driven by predator avoidance. Individual fitness in the model is strongly dependent on the presence of other phenotypes, such that two distinct types of evolved group can be produced by the same predation or foraging conditions, each stable against individual mutation. We draw analogies with multiple Nash equilibria theory of iterated games to explain and categorize these behaviours. Our model is sufficient to capture the complex behaviour of dynamic collective groups, yet is flexible enough to manifest evolutionary behaviour.

… , we define the notion of level of emergence, and propose to order comportments according … We also show how levels of emergence can be used to assess the redundancy in patterns. …

… model characteristics we distinguish collective and emergent … Emergent properties result from the activities of lower level … Emergent properties that are aggregational are those which …

… (IBM) extend the potential of ecological models to cope with spatial heterogeneity and … of individual-based modelling related to self-organisation processes and emergent properties in …

Proponents of individual-based modeling in ecology claim that their models explain the emergence of population-level behavior. This article argues that individual-based models have not, as yet, provided such explanations. Instead, individual-based models can and do demonstrate and explain the emergence of population-level behaviors from individual behaviors and interactions.

… The term ABM originally emerged in a computational context with applications in physics as well as applications in social sciences and economics. ABM often describe robotic …

… emerge. Unlike other approaches working on higher abstraction levels, individual-based models … First, a generic model structure for individual-based models operating on the basis of …

… Speciation is an emergent property of such models. … Given that an individual-based model is kept simple enough that … classical models can also be applied to individual-based models. …

Individual-based modelling (IBM) is an important option in ecology for the study of specific properties of complex ecological interaction networks. The main application of this model type is the analysis of population characteristics at high resolution. IBM also contributes to the advancement of ecological theory. One of the remarkable potentials of the approach is the possibility of studying self-organization and emergent properties that arise from individual actions on higher integration levels, especially on the population level. This review outlines the background and different application fields of individual-based models together with a short description of the technical implications of model setup. The limitations of this modelling approach result from the technical basis of model construction, which can handle a limited number of active entities only. Limits in biological knowledge also restrict the application of this model type. The paper presents some individual-based models that have been developed for different purposes and briefly discusses these models. Concerning the perspective of IBM, a coincidence with developments in artificial life research is explained. IBM shifts the focus of ecological analysis of dynamic systems from structurally fixed settings to the analysis of self-organizing interaction patterns that are variable in quantity and quality.

… and testing them with data just on ecosystems, we need to think about and model how ecosystem characteristics emerge from characteristics and behaviors of individuals. But when …

Ecologists urgently need a better ability to predict how environmental change affects biodiversity. We examine individual-based ecology (IBE), a research paradigm that promises better a predictive ability by using individual-based models (IBMs) to represent ecological dynamics as arising from how individuals interact with their environment and with each other. A key advantage of IBMs is that the basis for predictions—fitness maximization by individual organisms—is more general and reliable than the empirical relationships that other models depend on. Case studies illustrate the usefulness and predictive success of long-term IBE programs. The pioneering programs had three phases: conceptualization, implementation, and diversification. Continued validation of models runs throughout these phases. The breakthroughs that make IBE more productive include standards for describing and validating IBMs, improved and standardized theory for individual traits and behavior, software tools, and generalized instead of system-specific IBMs. We provide guidelines for pursuing IBE and a vision for future IBE research.

… individual-based models. The distinction is introduced between ‘pragmatic’ motivation, which uses the individual-based … theoretical issues which have emerged from the classical state …

Individual-based models simulate populations and communities by following individuals and their properties. They have been used in ecology for more than four decades, with their use and ubiquity in ecology growing rapidly in the last two decades. Individual-based models have been used for many applied or “pragmatic” issues, such as informing the protection and management of particular populations in specific locations, but their use in addressing theoretical questions has also grown rapidly, recently helping us to understand how the sets of traits of individual organisms influence the assembly of communities and food webs. Individual-based models will play an increasingly important role in questions posed by complex ecological systems.

… The individual-based modeling (IBM) approach has been repeatedly applied to assess … current lack of models where plasticity is an evolving trait. Future eco-evolutionary models should …

A spatiotemporal individual-based model (IBM) of roach (Rutilus rutilus) including bioenergetic principles was used to study emergent properties at the individual and the population …

… Of five models tested for hatching time, the best fit was provided by a three-… model which formed the basis of the individual-based model used to predict egg hatching and fry emergence. …

… Firstly, MANTA relied on an innovative modeling and simulation framework called EMF (… to implement multi-agent simulations. Secondly, the purpose of MANTA was not only to simulate …

… how to design a simulation, have two major drawbacks for our purpose : (1) they do not specifically address multi-agent based simulation, but rather computer simulation in general; (2) …

This paper presents a multi-agent model system to characterize land-use change dynamics. The replicable parameterization process should be useful to the development of simulation …

… This article presents an overview of multi-agent system models of land-use/cover change (… stylized hypotheses to empirically detailed simulation models appropriate for scenario and …

… Simulation and Implementation (PASSIM), a simulation-based development process for Multi-agent Systems … and a Statecharts-based simulation methodology supporting functional and …

Simulation has become an indispensable tool for researchers to explore systems without having recourse to real experiments. Depending on the characteristics of the modeled system, methods used to represent the system may vary. Multi-agent systems are, thus, often used to model and simulate complex systems. Whatever modeling type used, increasing the size and the precision of the model increases the amount of computation, requiring the use of parallel systems when it becomes too large. In this paper, we focus on parallel platforms that support multi-agent simulations. Our contribution is a survey on existing platforms and their evaluation in the context of high performance computing. We present a qualitative analysis, mainly based on platform properties, then a performance comparison using the same agent model implemented on each platform.

Multi-agent Systems (MAS) offer a conceptual approach to include multi-actor decision making into models of land use change. The main goal is to explore the use of MAS to simulate …

… Multi-agent systems are an emerging computing paradigm for the construction of such simulations. During the last two years, we have used multiagent simulations for three different …

… Several electricity market simulators have been introduced in recent years with the purpose … (Multi-Agent System for Competitive Electricity Markets), an electricity market simulator with …

This paper proposes a review of the development and use of multi-agent simulations (MAS) for ecosystem management. The use of this methodology and the associated tools …

… dynamic heterogeneous agent models (HAMs) in economics and finance. Emphasis is given to simple models that, … Most of these models are behavioral models with boundedly rational …

… The model explicitly incorporates the decentralized interaction of heterogeneous agents across different sectors and regions. The modeling of individual behavior is based on heuristics …

… agents and their links in a networked economy. We believe that there has to be some degree of heterogeneity of agents. They … A model with heterogeneous agents (ABM) interacting in a …

In this paper we study the effectiveness of different types of cohesion policies with respect to convergence of regions. A two-region agent-based macroeconomic model is used to …

… Recently, boundedly rational and heterogeneous agent models … Here, we are interested in how well the proposed models … of some simple versions of such a model by the use of efficient …

The thesis of this essay is that, in heterogeneous agent macroeconomics, the assumption of rational expectations about equilibrium prices is unrealistic and should be replaced. Rational expectations imply that decision makers forecast equilibrium prices like interest rates by forecasting cross-sectional distributions. This leads to an extreme version of the curse of dimensionality: dynamic programming problems in which the entire distribution is a state variable (‘Master equation’ a.k.a. ‘Monster equation’). Frontier computational methods struggle with these infinite-dimensional Bellman equations, making it implausible that real-world agents solve the associated decision problems. These difficulties also limit the applicability of the heterogeneous-agent approach to central questions in macroeconomics – those involving aggregate risk and non-linearities such as financial crises. This troublesome feature of the rational expectations assumption poses a challenge: what should replace it? I outline three criteria for alternative approaches: (1) computational tractability, (2) consistency with empirical evidence, and (3) (some) immunity to the Lucas critique. I then discuss several promising directions, including temporary equilibrium approaches, incorporating survey expectations, least-squares learning, and reinforcement learning.

… permits a distinctive approach to social science for which the term “generative” is suitable. In … deductive” science are given. Then, the following specific contributions to social science are …

Agent-based computational modeling is changing the face of social science. In Generative Social Science , Joshua Epstein argues that this powerful, novel technique permits the social sciences to meet a fundamentally new standard of explanation, in which one "grows" the phenomenon of interest in an artificial society of interacting agents: heterogeneous, boundedly rational actors, represented as mathematical or software objects. After elaborating this notion of generative explanation in a pair of overarching foundational chapters, Epstein illustrates it with examples chosen from such far-flung fields as archaeology, civil conflict, the evolution of norms, epidemiology, retirement economics, spatial games, and organizational adaptation. In elegant chapter preludes, he explains how these widely diverse modeling studies support his sweeping case for generative explanation. This book represents a powerful consolidation of Epstein's interdisciplinary research activities in the decade since the publication of his and Robert Axtell's landmark volume, Growing Artificial Societies . Beautifully illustrated, Generative Social Science includes a CD that contains animated movies of core model runs, and programs allowing users to easily change assumptions and explore models, making it an invaluable text for courses in modeling at all levels.

… Most of today’s social science subscribes at least loosely to a Humean regularity … generative explanations stems from the difficulties of finding and isolating regularities in complex social …

Powered by advanced information technology, more and more complex systems are exhibiting characteristics of the cyber-physical-social systems (CPSS). In this context, computational experiments method has emerged as a novel approach for the design, analysis, management, control, and integration of CPSS, which can realize the causal analysis of complex systems by means of “algorithmization” of “counterfactuals”. However, because CPSS involve human and social factors (e.g., autonomy, initiative, and sociality), it is difficult for traditional design of experiment (DOE) methods to achieve the generative explanation of system emergence. To address this challenge, this paper proposes an integrated approach to the design of computational experiments, incorporating three key modules: 1) Descriptive module: Determining the influencing factors and response variables of the system by means of the modeling of an artificial society; 2) Interpretative module: Selecting factorial experimental design solution to identify the relationship between influencing factors and macro phenomena; 3) Predictive module: Building a meta-model that is equivalent to artificial society to explore its operating laws. Finally, a case study of crowd-sourcing platforms is presented to illustrate the application process and effectiveness of the proposed approach, which can reveal the social impact of algorithmic behavior on “rider race”.

… The case of complexity theory in this regard reflects this and its current development as generative social science points up this logic. Over the last fifty years, there has been a profound …

The agent-based model is the principal scientific instrument of generative social science. Typically, we design completed agents-fully endowed with rules and parameters-to grow macroscopic target patterns from the bottom up. Inverse generative science (iGSS) stands this approach on its head: Rather than handcrafting completed agents to grow a target-the forward problem-we start with the macro-target and evolve micro-agents that generate it, stipulating only primitive agent-rule constituents and permissible combinators. Rather than specific agents as designed inputs, we are interested in agents-indeed, families of agents-as evolved outputs. This is the backward problem and tools from Evolutionary Computing can help us solve it. In this overarching essay of the current JASSS Special Section, Part 1 discusses the motivation for iGSS. Part 2 discusses its goals, as distinct from other approaches. Part 3 discusses how to do it concretely, previewing the five iGSS applications that follow. Part 4 discusses several foundational issues for agent-based modeling and economics. Part 5 proposes a central future application of iGSS: to evolve explicit formal alternatives to the Rational Actor, with Agent_Zero as one possible point of evolutionary departure. Conclusions and future research directions are offered in Part 6. Looking 'backward to the future,' I also include, as Appendices, a pair of 1992 memoranda to the then President of the Santa Fe Institute on the forward (growing artificial societies from the bottom up) and backward (iGSS) problems.

Since its articulation in 2009, Computational Social Science (CSS) has grown into a mature interdisciplinary paradigm, shaped first by mobile media-generated digital traces and more recently by generative AI. With over a decade of development, CSS has expanded its scope across data, methods, and theory: data sources have evolved from mobile traces to multimodal records; methods have diversified from surveys and experiments to agent-based modeling, network analysis, and computer vision; and theory has advanced by revisiting classical questions and modeling emergent digital phenomena. Generative AI further enhances CSS through scalable annotation, experimental design, and simulation, while raising challenges of validity, reproducibility, and ethics. The evolutionary logic of CSS lies in coupling theory, models, and data, balancing innovation with normative safeguards to build cumulative knowledge and support responsible digital governance.

Generative mechanism-based models of social systems, such as those represented by agent-based simulations, require that intra-agent equations (or rules) be specified. However there are often many different choices available for specifying these equations, which can still be interpreted as falling within a particular class of mechanisms. Whilst it is important for a generative model to reproduce historically observed dynamics, it is also important for the model to be theoretically enlightening. Genetic programs (our own included) often produce concatenations that are highly predictive but are complex and hard to interpret theoretically. Here, we develop a new method - based on multi-objective genetic programming - for automating the exploration of both objectives simultaneously. We demonstrate the method by evolving the equations for an existing agent-based simulation of alcohol use behaviors based on social norms theory, the initial model structure for which was developed by a team of human modelers. We discover a trade-off between empirical fit and theoretical interpretability that offers insight into the social norms processes that influence the change and stasis in alcohol use behaviors over time.

… Although we focus mainly on the complexity literature, we also take … complexity ideas. Based on these ideas selected from complexity theory, we then present the process of generative …

… We begin with a brief historical sketch of the shift from“factors” to “actors” in computational sociology thatshows how agent-based modeling differs fundamentally from earlier …

… applications of agent-based models (ABMs) in sociology and, in particular, their explanatory achievements and methodological insights. These applications have helped sociologists to …

We discuss two computational approaches of particular significance for rigorous sociology, Agent-Based Computational Modeling (ABCM) and Computational Social Science (CSS). CSS exploits novel sources of large-scale data from, for example, the Internet, telephone-communication records, or population register data, studying digital traces of social interaction with great precision. ABCM uses computer simulation to study how social regularities can arise from complex interactions among interdependent individuals. CSS and ABCM share a strong focus on computational methods, but only a few contributions combine them. We briefly introduce both approaches and argue that they can strongly benefit from more interaction and integration. ABCM can address the generalizability and theoretical explanation of empirical patterns identified in CSS, whilst empirical CSS can help validate and calibrate otherwise abstract models from ABCM. We discuss examples of a successful combination of both approaches and address directions for more theoretical and methodological integration in the future.

… We place a particular emphasis on empirically calibrated agent-based models which have … Conventional agent-based models (ABMs) have occupied a niche space in sociology for …

Analytical sociology focuses on social interactions among individuals and the hard-to-predict aggregate outcomes they bring about. It seeks to identify generalizable mechanisms giving rise to emergent properties of social systems which, in turn, feed back on individual decision-making. This research program benefits from computational tools such as agent-based simulations, machine learning, and large-scale web experiments, and has considerable overlap with the nascent field of computational social science. By providing relevant analytical tools to rigorously address sociology’s core questions, computational social science has the potential to advance sociology in a similar way that the introduction of econometrics advanced economics during the last half century. Computational social scientists from computer science and physics often see as their main task to establish empirical regularities which they view as “social laws.” From the perspective of the social sciences, references to social laws appear unfounded and misplaced, however, and in this article we outline how analytical sociology, with its theory-grounded approach to computational social science, can help to move the field forward from mere descriptions and predictions to the explanation of social phenomena.

… I discuss the model by Goldberg and Stein (2018) as an example where agents in an agent-based model are endowed with an associative matrix to interpret and give meaning to …

Agent-based modeling has become increasingly popular in recent years, but there is still no codified set of recommendations or practices for how to use these models within a program of empirical research. This article provides ideas and practical guidelines drawn from sociology, biology, computer science, epidemiology, and statistics. We first discuss the motivations for using agent-based models in both basic science and policy-oriented social research. Next, we provide an overview of methods and strategies for incorporating data on behavior and populations into agent-based models, and review techniques for validating and testing the sensitivity of agent-based models. We close with suggested directions for future research.

… Agent-based modelers used to form a community of their … using agent-based modeling are no longer “agent-based … to see innovative research that uses agent-based models in novel …

A lengthy and intensive debate about the role of sociology in agent based social simulation dominated the email list simsoc@jiscmail.ac.uk during the autumn of 2000. The debate …

… Laver (2005) points out that “using agent-based models means that we must set on one side … The appeal of agent-based modeling is not to abandon the idea of rational choice in total …

… agent-based computational model. However, some details in Manzo’s scheme and in his texts suggest his approach is more likely to recognize the relevance of the description and …

This article addresses knowledge transfer dynamics in agent-based computational social science. The goal of the text is twofold. First, it describes the tensions arising from the convergence of different disciplinary traditions in the emergence of this new area of study and, second, it shows how these tensions are dealt with through the articulation of distinctive practices of knowledge production and transmission. To achieve this goal, three major instances of knowledge transfer dynamics in agent-based computational social science are analysed. The first instance is the emergence of the research field. Relations of knowledge transfer and cross-fertilisation between agent-based computational social science and wider and more established disciplinary areas: complexity science, computational science and social science, are discussed. The second instance is the approach to scientific modelling in the field. It is shown how the practice of agent-based modelling is affected by the conflicting coexistence of shared methodological commitments transferred from both empirical and formal disciplines. Lastly, the third instance pertains internal practices of knowledge production and transmission. Through the discussion of these practices, the tensions arising from converging dissimilar disciplinary traditions in agent-based computational social science are highlighted.

In the first part of the paper, the field of agent-based modeling (ABM) is discussed focusing on the role of generative theories, aiming at explaining phenomena by growing them. After a brief analysis of the major strengths of the field some crucial weaknesses are analyzed. In particular, the generative power of ABM is found to have been underexploited, as the pressure for simple recipes has prevailed and shadowed the application of rich cognitive models. In the second part of the paper, the renewal of interest for Computational Social Science (CSS) is focused upon, and several of its variants, such as deductive, generative, and complex CSS, are identified and described. In the concluding remarks, an interdisciplinary variant, which takes after ABM, reconciling it with the quantitative one, is proposed as a fundamental requirement for a new program of the CSS.

The advent of Large Language Models (LLMs) offers to transform research across natural and social sciences, offering new paradigms for understanding complex systems. In particular, Generative Agent-Based Models (GABMs), which integrate LLMs to simulate human behavior, have attracted increasing public attention due to their potential to model complex interactions in a wide range of artificial environments. This paper briefly reviews the disruptive role LLMs are playing in fields such as network science, evolutionary game theory, social dynamics, and epidemic modeling. We assess recent advancements, including the use of LLMs for predicting social behavior, enhancing cooperation in game theory, and modeling disease propagation. The findings demonstrate that LLMs can reproduce human-like behaviors, such as fairness, cooperation, and social norm adherence, while also introducing unique advantages such as cost efficiency, scalability, and ethical simplification. However, the results reveal inconsistencies in their behavior tied to prompt sensitivity, hallucinations and even the model characteristics, pointing to challenges in controlling these AI-driven agents. Despite their potential, the effective integration of LLMs into decision-making processes -whether in government, societal, or individual contexts- requires addressing biases, prompt design challenges, and understanding the dynamics of human-machine interactions. Future research must refine these models, standardize methodologies, and explore the emergence of new cooperative behaviors as LLMs increasingly interact with humans and each other, potentially transforming how decisions are made across various systems.

… Agent-based modeling (ABM) and simulation supports representation of complex systems … between autonomous dynamic agents, the nonlinear interactions between the agents and the …

Information about a system’s internal interactions is important to modeling the system’s dynamics. This study examines the finer categories of the information definition and explores the features of a type of local information that describes the internal interactions of a system. Based on the results, a dual-space agent and information modeling framework (AIM) is developed by explicitly distinguishing an information space from the material space. The two spaces can evolve both independently and interactively. The dual-space framework can provide new analytic methods for agent based models (ABMs). Three examples are presented including money distribution, individual’s economic evolution, and artificial stock market. The results are analyzed in the dual-space, which more clearly shows the interactions and evolutions within and between the information and material spaces. The outcomes demonstrate the wide-ranging applicability of using the dual-space AIMs to model and analyze a broad range of interactive and intelligent systems.

… A complex system is characterized by a large number of interacting components (eg agents … Complex systems are hard to simulate or model using traditional computational approaches …

Abstract A number of modeling and simulation tools have been developed in the domain of Natural Disasters. In these situations, several research teams may make an intervention and that have to coordinate their activities in order to save the maximum number of lives. To this end, they have to define an organizational structure and adopt management policies to improve their performance. The organizational structure and the policies are important elements that have to be taken into account to simulate a real emergency activity. To facilitate the design of these simulations, an agent-based methodological framework for complex system (Supply Chain, Natural Disaster) is proposed. The main contribution of the framework is that it will reflect the organizational structure and policies within the simulation, and which involves the integration truly dynamic dimension of this organization. We propose also a specification of the translation process to ensure the transition between various models that are proposed in the methodological framework.

… Agent-based complex systems are dynamic networks of many interacting agents; examples include ecosystems, financial markets, and cities. The search for general principles …

… A somewhat parallel development occurred within the study of complex systems. From … out of the mantra of “simple components, complex systems.” Indeed, in each of these domains …

… paradigm for complex system modeling. We argue that complex agent networks are able to capture both individual-level dynamics as well as global-level properties of a complex system…

… about an agent-based model of relative deprivation, with the concept of “generative causality” … more systematically the role of agent-based computational modeling for causal inference. …

ABSTRACT Even though agent-based modelling is seen as committing to a mechanistic, generative type of causation, the methodology allows for representing many other types of causal explanations. Agent-based models are capable of integrating diverse causal relationships into coherent causal mechanisms. They mirror the crucial, multi-level component of emergent phenomena and recognize the important role of single-level causes without limiting the scope of the offered explana- tion. Implementing various types of causal relationships to complement the generative causation offers insight into how a multi-level phenomenon happens and allows for building more complete causal explanations. The capacity to work with multiple approaches to causality is crucial when tackling the complex problems of the modern world.

… Causal Assumptions The causal module in this study is used for counterfactual reasoning … Large language models empowered agent-based modeling and simulation: A survey and …

Large language models (LLMs) can generate high-level diverse phenomena without explicitly programmed rules. This capability has led to their adoption within different agent-based models (ABMs) and social simulations. Recent research aim to test whether they are capable of generating different phenomena of interest, for example, human behavior on social media platforms or performance in game-theoretic scenarios. However, capability, prediction, and explanation are different - drawing from the philosophy of science and mechanisms literature, explanation requires showing, to some degree, how a phenomenon is produced by related organized entities and activities. For modelers, describing the characteristics of an experiment or whether a simulation provides progress in capability (or explanation), can be difficult without being grounded in potentially distant research areas. We integrate recent work on LLM-ABMs with contemporary philosophy of science literature and make two main contributions. First, we gather insights from modeling and mechanisms literature and use them to operationalize a definition of ‘plausibility’ in a four-level scale. Our scale separates the evaluation of a model's generative sufficiency (ability to reproduce a phenomenon) from its mechanistic plausibility (how the phenomenon could be produced), and clarifies the distinct roles of different models, such as predictive and explanatory ones. We introduce this as the Mechanism Plausibility Scale. Second, we discuss the early wave of LLM-ABM research and find that papers often conflate evidence of Agent-level functionality with claims about emergent ABM-level phenomenon, relying on ‘believability’ metrics that focus on generative sufficiency. Our discussion section speaks on how these findings echo long-standing problems in classical ABM, historical harms caused by these issues, and broader ethical and epistemic concerns about using LLMs in modeling. Using the findings from our review, we offer the scale as a practical heuristic in the form of a checklist which can clarify how simulations at different levels of plausibility may be useful. We hope the activity of filling out the scale will help new modelers ground the epistemic contribution of their simulations.

Recent applications of artificial intelligence in economics and finance have been dominated by predictive machine learning approaches that deliver impressive forecasting performance in stable environments but offer limited support for explanation, policy evaluation, and structural change analysis. While such models excel at detecting correlations, they struggle to address causal mechanisms, counterfactual reasoning, and emergent dynamics that are central to economic decision-making and policy design. This paper argues that these limitations stem from an overreliance on prediction-oriented AI and proposes an integrated framework that combines causal AI, generative AI, and agent-based AI to better align artificial intelligence with economic reasoning. The framework synthesizes advances in causal inference, deep generative modeling, and computational economics to move beyond black-box prediction toward systems capable of explanation, simulation, and intervention. Specifically, the proposed approach emphasizes three capabilities that purely predictive models lack: identification of policy-invariant causal relationships, robust counterfactual and stress-test analysis under structural change, and the modeling of emergent macroeconomic outcomes arising from heterogeneous agent interactions. By unifying these paradigms, the paper provides a conceptual foundation for AI systems that support policy evaluation, scenario analysis, and institutional design in complex economic and financial systems. The paper concludes by outlining ethical, governance, and institutional considerations and by proposing a research agenda for developing economically grounded, transparent, and policy-relevant AI tools that complement rather than replace economic theory.

In this paper, we investigate the use of Generative Adversarial Networks (GAN) to model agent behavior in agent-based models. We hereby focus on use cases in which an agent's decision-making process may only be modeled from data, but it is infeasible to be modeled causally. In these situations, meta-models are often the only way to quantitatively parameterize the agent-based model. However, methods that capture not only deterministic relationships but also stochastic uncertainty are rare. Since GANs are well known for their property to generate pseudo-random-numbers for complex distributions, we explore pros and cons of this strategy for modeling a delay-process in a large-scale agent-based SARS-CoV-2 simulation model.

… , have made substantial contributions to causal inference under relatively static settings, yet … to establish empirical validation for generative agent-based modeling. To facilitate practical …

The advent of generative agents (GAs) based on large language models (LLMs) has significantly influenced the evolution of agent-based modeling (ABM), offering new perspectives across various domains, including engineering and social sciences. This article provides an extensive overview of the integration of GAs into ABMs, emphasizing the advancements and emerging challenges in their validation. Traditional ABMs, characterized by their simplistic yet powerful approach to modeling complex systems, have been redefined with the introduction of GAs. This new generation of agents is often equipped with conversational capabilities. These agents, capable of simulating believable human behaviors and interactions, present unique opportunities and hurdles, especially in urban simulations and social dynamics. We explore the nuanced differences between traditional ABMs and ABMs populated by GAs—called GABMs. We delve into the state-of-the-art implementations of GAs, and review various validation methods. Through this comprehensive examination, we aim to shed light on the potential and limitations of GAs, advocating for the design of hybrid ABM-GABM approaches and systematic validation.

Calls for the adoption of complex systems approaches, including agent-based modeling, in the field of epidemiology have largely centered on the potential for such methods to examine complex disease etiologies, which are characterized by feedback behavior, interference, threshold dynamics, and multiple interacting causal effects. However, considerable theoretical and practical issues impede the capacity of agent-based methods to examine and evaluate causal effects and thus illuminate new areas for intervention. We build on this work by describing how agent-based models can be used to simulate counterfactual outcomes in the presence of complexity. We show that these models are of particular utility when the hypothesized causal mechanisms exhibit a high degree of interdependence between multiple causal effects and when interference (i.e., one person's exposure affects the outcome of others) is present and of intrinsic scientific interest. Although not without challenges, agent-based modeling (and complex systems methods broadly) represent a promising novel approach to identify and evaluate complex causal effects, and they are thus well suited to complement other modern epidemiologic methods of etiologic inquiry.

… Those models can replicate actual dynamics to provide causal inference. This requires a … Agent-based models (ABMs) take a bottom-up approach for modelling systems, with macro-…