Towards Agentic Agent-based Models: Feasibility, Performance, and Statistical Model Checking

• URL: http://arxiv.org/abs/2607.17948v1
• Date: Mon, 20 Jul 2026 13:49:51 GMT
• Title: Towards Agentic Agent-based Models: Feasibility, Performance, and Statistical Model Checking
• Abstract summary: Agent-based models (ABMs) rely on simple, explicit and reproducible rules for individual decision making.<n>Recent advances in large language models (LLMs) make it tempting to replace, enrich, or perturb these rules with LLM-based agentic capabilities.<n>We investigate how introducing LLM-driven decisions affect the reliability, computational cost, and behavior of ABM simulations.
• Score: 0.42025549992700273
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agent-based models (ABMs) rely on simple, explicit and reproducible rules for individual decision making, while complex collective behavior emerges from interactions among agents. Recent advances in large language models (LLMs) make it tempting to replace, enrich, or perturb these rules with LLM-based agentic capabilities. However, this raises a methodological question: how does introducing LLM-driven decisions affect the reliability, computational cost, and behavior of ABM simulations? We investigate this for Mesa ABM models, a popular Python library for ABMs, analyzed by statistical model checking. Building on Mesa's integration with the statistical model checker MultiVeStA, we extend the classical Schelling segregation model with a hybrid population: ordinary agents classify neighbors using the standard symbolic rule, while one agent delegates this task to an LLM through tool calls. The LLM-enabled agent receives natural-language descriptions of neighboring agents and invokes tools that increment counters of similar/different neighbors; these counters determine its happiness according to the original Schelling dynamics. This provides a minimal but controlled setting where the semantic, operational, and computational behavior of LLM-based decisions can be studied inside an otherwise standard ABM. We report preliminary experiments with locally served LLMs of different sizes, showing that smaller models may fail simple semantic classification experiments or become operationally unusable during repeated tool-call generation, while larger tested models pass these preliminary checks. We discuss how statistical model checking can estimate classical ABM observables and quantify the impact of introducing agentic LLM components into simulation models.

Related papers

• AgoraSim: A Hybrid Agent-Based Modeling Framework [4.857286974497513]
  AgoraSim is a hybrid agent-based modeling framework for scenario-oriented social reaction analysis.<n>It runs ratio-controlled populations that mix LLM, vision-language, custom-endpoint, random, and classical agents.<n>All agents emit a shared structured decision object, enabling common action spaces, interaction protocols, metrics, and audit records.
  arXiv  Detail & Related papers  (2026-07-07T08:37:17Z)
• Deliberate Evolution: Agentic Reasoning for Sample-Efficient Symbolic Regression with LLMs [52.89778838903305]
  Deliberate Evolution (DE) is an agentic framework that decouples symbolic generation from search control.<n>Experiments on LLM-SRBench show that DE consistently outperforms representative LLM-based SR baselines across diverse scientific domains.
  arXiv  Detail & Related papers  (2026-06-03T02:22:16Z)
• Learning POMDP World Models from Observations with Language-Model Priors [52.11151769796862]
  Partially-observable Markov decision processes (POMDPs) provide a flexible modeling class for internal world models.<n>We ask whether language-model priors can reduce costly interaction by leveraging prior knowledge.<n>We show that emphPinductor matches the performance and sample efficiency of LLM-based POMDP learning methods.
  arXiv  Detail & Related papers  (2026-05-13T16:18:15Z)
• CTTS: Collective Test-Time Scaling [58.564620942591866]
  Test-time scaling (TTS) has emerged as a promising, training-free approach for enhancing large language model (LLM) performance.<n>We introduce Collective Test-Time Scaling (CTTS) to overcome the dominant single test-time scaling (STTS) paradigm.<n>CTTS-MM is a novel framework that operationalizes multi-agent and multi-reward collaboration.
  arXiv  Detail & Related papers  (2025-08-05T11:19:08Z)
• World Modelling Improves Language Model Agents [11.081954466884392]
  DyMo is a method that augments large language models with a state prediction capability alongside function calling during post-training.<n>On the Berkeley Calling Leaderboard V2, DyMo improves success rates and significantly reduces hallucinations.
  arXiv  Detail & Related papers  (2025-06-03T14:20:59Z)
• Applying Large Language Models to Travel Satisfaction Analysis [2.5105418815378555]
  This study uses household survey data collected in Shanghai to identify the existence and source of misalignment between Large Language Models (LLMs) and humans.<n>LLMs have strongcapabilities in contextual understanding and generalization, significantly reducing dependence on task-specific data.<n>We propose an LLM-based modeling approach that can be applied to model travel behavior with small sample sizes.
  arXiv  Detail & Related papers  (2025-05-29T09:11:58Z)
• Improving Reasoning Performance in Large Language Models via Representation Engineering [2.0099933815960256]
  We propose a representation engineering approach for large language models (LLMs)<n>Model activations are read from the residual stream of an LLM when processing a reasoning task.<n>We show that an LLM can, to a certain degree, be controlled to improve its perceived reasoning ability by modulating activations.
  arXiv  Detail & Related papers  (2025-04-28T04:58:43Z)
• Model Utility Law: Evaluating LLMs beyond Performance through Mechanism Interpretable Metric [99.56567010306807]
  Large Language Models (LLMs) have become indispensable across academia, industry, and daily applications.<n>One core challenge of evaluation in the large language model (LLM) era is the generalization issue.<n>We propose Model Utilization Index (MUI), a mechanism interpretability enhanced metric that complements traditional performance scores.
  arXiv  Detail & Related papers  (2025-04-10T04:09:47Z)
• FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models [79.41859481668618]
  Large Language Models (LLMs) have significantly advanced the fact-checking studies.<n>Existing automated fact-checking evaluation methods rely on static datasets and classification metrics.<n>We introduce FACT-AUDIT, an agent-driven framework that adaptively and dynamically assesses LLMs' fact-checking capabilities.
  arXiv  Detail & Related papers  (2025-02-25T07:44:22Z)
• LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization [59.75242204923353]
  We introduce LLM-Lasso, a framework that leverages large language models (LLMs) to guide feature selection in Lasso regression.<n>LLMs generate penalty factors for each feature, which are converted into weights for the Lasso penalty using a simple, tunable model.<n>Features identified as more relevant by the LLM receive lower penalties, increasing their likelihood of being retained in the final model.
  arXiv  Detail & Related papers  (2025-02-15T02:55:22Z)
• On the limits of agency in agent-based models [13.130587222524305]
  Agent-based modeling offers powerful insights into complex systems, but its practical utility has been limited by computational constraints. Recent advancements in large language models (LLMs) could enhance ABMs with adaptive agents, but their integration into large-scale simulations remains challenging. We present LLM archetypes, a technique that balances behavioral complexity with computational efficiency, allowing for nuanced agent behavior in large-scale simulations.
  arXiv  Detail & Related papers  (2024-09-14T04:17:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.