Pith. sign in

REVIEW 9 cited by

Do Large Language Models Solve the Problems of Agent-Based Modeling? A Critical Review of Generative Social Simulations

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2504.03274 v1 pith:AL3GHU23 submitted 2025-04-04 cs.MA cs.AI

classification cs.MAcs.AI
keywords abmsgenerativesocialllmsmodelsadequatelyagent-basedapproach
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Recent advancements in AI have reinvigorated Agent-Based Models (ABMs), as the integration of Large Language Models (LLMs) has led to the emergence of ``generative ABMs'' as a novel approach to simulating social systems. While ABMs offer means to bridge micro-level interactions with macro-level patterns, they have long faced criticisms from social scientists, pointing to e.g., lack of realism, computational complexity, and challenges of calibrating and validating against empirical data. This paper reviews the generative ABM literature to assess how this new approach adequately addresses these long-standing criticisms. Our findings show that studies show limited awareness of historical debates. Validation remains poorly addressed, with many studies relying solely on subjective assessments of model `believability', and even the most rigorous validation failing to adequately evidence operational validity. We argue that there are reasons to believe that LLMs will exacerbate rather than resolve the long-standing challenges of ABMs. The black-box nature of LLMs moreover limit their usefulness for disentangling complex emergent causal mechanisms. While generative ABMs are still in a stage of early experimentation, these findings question of whether and how the field can transition to the type of rigorous modeling needed to contribute to social scientific theory.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Can Generative AI agents behave like humans? Evidence from laboratory market experiments

    econ.GN 2025-05 conditional novelty 7.0 of 10

    With at least three steps of memory and high randomness, large language model agents broadly replicate human forecasting patterns in positive and negative feedback markets, but are less heterogeneous than humans.

  2. Empirical Grounding Improves the Realism of LLM Agents Simulating Human Behavior During Disruptions

    cs.AI 2026-07 conditional novelty 6.0 of 10

    Grounding LLM agents with ACS demographics and ATUS time-use routines substantially improved reproduction of observed activity profiles under normal and heatwave conditions in Philadelphia, though over half of the hea...

  3. Large language models replicate and predict human cooperation across experiments in game theory

    cs.AI 2025-11 conditional novelty 6.0 of 10

    Llama-3.1-8B with a multi-step reasoning-and-filter prompt reproduces human cooperation rates across 121 dyadic games (MSD=0.031, r=0.89), outperforming Nash-equilibrium predictions (MSD=0.096, r=0.78).

  4. CoBAD: Modeling Collective Behaviors for Human Mobility Anomaly Detection

    cs.LG 2025-08 conditional novelty 6.0 of 10

    CoBAD detects collective mobility anomalies (unexpected co-occurrence and absence) by pre-training a two-stage attention model over collective event sequences and event graphs.

  5. Large Language Models for Agent-Based Modelling: Current and possible uses across the modelling cycle

    cs.MA 2025-07 conditional novelty 6.0 of 10

    A structured review showing that current LLM use in agent-based modelling is concentrated in implementation, with untapped but risky potential across problem formulation, conceptualization, verification, validation, i...

  6. LLM-Based Social Simulations Require a Boundary

    cs.CY 2025-06 conditional novelty 6.0 of 10

    LLM-based social simulations are scientifically useful only within boundaries set by behavioral variance, and current validation practice under-checks variance.

  7. Modeling Social Dynamics with an LLM-Enabled Agent Based Network-Dynamic (LAND) Model

    cs.AI 2026-08 reject novelty 4.0 of 10

    A large LLM-powered simulation of a fictional song contest claims coordination and influence emerge from network-narrative feedback, but the supporting analysis contains internal contradictions and unreleased artifacts.

  8. A Large Language Model-Driven Agent-Based Modeling Framework with Multi-Round Communication for Simulating Vaccine Opinion Dynamics

    cs.MA 2026-07 conditional novelty 4.0 of 10

    An LLM-driven agent-based model with multi-round dialogue reproduces non-linear social influence patterns in vaccination opinion dynamics, with memory increasing resistance and prompt diversity increasing adoption.

  9. Large Language Models for History, Philosophy, and Sociology of Science: Interpretive Uses, Methodological Challenges, and Critical Perspectives

    cs.CL 2025-06 conditional novelty 3.0 of 10

    A position paper arguing that LLMs can enhance interpretive research in history, philosophy, and sociology of science, but only with model literacy, domain-specific benchmarks, and critical reflection.

Pith tools