AgentSUMO: An Agentic Framework for Interactive Simulation Scenario Generation in SUMO via Large Language Models

• URL: http://arxiv.org/abs/2511.06804v1
• Date: Mon, 10 Nov 2025 07:46:12 GMT
• Title: AgentSUMO: An Agentic Framework for Interactive Simulation Scenario Generation in SUMO via Large Language Models
• Abstract summary: This study proposes an agentic framework for interactive simulation scenario generation via large language models.<n>AgentSUMO departs from imperative, command-driven execution by introducing an adaptive reasoning layer that interprets user intents, assesses task complexity, infers missing parameters, and formulates executable simulation plans.<n> Experiments on urban networks in Seoul and Manhattan demonstrate that the agentic workflow achieves substantial improvements in traffic flow metrics while maintaining accessibility for non-expert users.
• Score: 4.892076282924386
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The growing complexity of urban mobility systems has made traffic simulation indispensable for evidence-based transportation planning and policy evaluation. However, despite the analytical capabilities of platforms such as the Simulation of Urban MObility (SUMO), their application remains largely confined to domain experts. Developing realistic simulation scenarios requires expertise in network construction, origin-destination modeling, and parameter configuration for policy experimentation, creating substantial barriers for non-expert users such as policymakers, urban planners, and city officials. Moreover, the requests expressed by these users are often incomplete and abstract-typically articulated as high-level objectives, which are not well aligned with the imperative, sequential workflows employed in existing language-model-based simulation frameworks. To address these challenges, this study proposes AgentSUMO, an agentic framework for interactive simulation scenario generation via large language models. AgentSUMO departs from imperative, command-driven execution by introducing an adaptive reasoning layer that interprets user intents, assesses task complexity, infers missing parameters, and formulates executable simulation plans. The framework is structured around two complementary components, the Interactive Planning Protocol, which governs reasoning and user interaction, and the Model Context Protocol, which manages standardized communication and orchestration among simulation tools. Through this design, AgentSUMO converts abstract policy objectives into executable simulation scenarios. Experiments on urban networks in Seoul and Manhattan demonstrate that the agentic workflow achieves substantial improvements in traffic flow metrics while maintaining accessibility for non-expert users, successfully bridging the gap between policy goals and executable simulation workflows.

Related papers

• SenseWalk: Agent-Based Semantic Trajectory Simulation Powered by Large Language Models in Zoned Environments [6.133926295796511]
  $SenseWalk$ is an interactive system that supports simulating semantic trajectories by LLM-powered agents.<n>We develop a simulation workflow that combines LLMs and the social force model to balance physical plausibility and semantic coherence.
  arXiv  Detail & Related papers  (2026-07-01T14:25:47Z)
• Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants [85.1155076383488]
  Pare is a framework for building and evaluating proactive agents in digital environments.<n>Pare-Bench is a benchmark of 143 diverse tasks spanning communication, productivity, scheduling, and lifestyle apps.
  arXiv  Detail & Related papers  (2026-04-01T12:53:01Z)
• SimMOF: AI agent for Automated MOF Simulations [1.5280683380195148]
  Metal-organic frameworks (MOFs) offer a vast design space.<n>SimMOF automates a large language model based multi agent framework that translates end-to-end MOF simulation from natural language queries.<n>SimMOF user requests into dependency aware plans, generates runnable inputs, orchestrates multiple agents to execute simulations, and summarizes results aligned to the user query.
  arXiv  Detail & Related papers  (2026-03-31T02:08:50Z)
• Position: AI Agents Are Not (Yet) a Panacea for Social Simulation [62.891898598784415]
  Recent advances in large language models (LLMs) have spurred growing interest in using LLM-integrated agents for social simulation.<n>This position paper argues that LLM-based agents are not (yet) a panacea for social simulation.
  arXiv  Detail & Related papers  (2026-02-19T06:35:07Z)
• TrafficSimAgent: A Hierarchical Agent Framework for Autonomous Traffic Simulation with MCP Control [21.810319218786262]
  TrafficSimAgent is an expert in experiment design and decision optimization for general-purpose traffic simulation tasks.<n>The framework facilitates execution through cross-level collaboration among expert agents.<n>It consistently produces reasonable outcomes even when user instructions are ambiguous.
  arXiv  Detail & Related papers  (2025-12-24T06:48:04Z)
• TongSIM: A General Platform for Simulating Intelligent Machines [59.27575233453533]
  Embodied intelligence focuses on training agents within realistic simulated environments.<n>TongSIM is a high-fidelity, general-purpose platform for training and evaluating embodied agents.
  arXiv  Detail & Related papers  (2025-12-23T10:00:43Z)
• Modeling realistic human behavior using generative agents in a multimodal transport system: Software architecture and Application to Toulouse [0.0]
  This paper presents an architecture for modeling realistic human mobility behavior in complex multimodal transport systems.<n>We apply Large Language Models (LLMs) within an agent-based simulation to capture decision-making in a real urban setting.<n>Result show that agents not only make context-aware transport decisions but also form habits over time.
  arXiv  Detail & Related papers  (2025-10-22T11:45:44Z)
• Integrating LLM and Diffusion-Based Agents for Social Simulation [28.21329943306884]
  We propose a hybrid simulation framework that strategically integrates large language model (LLM)-driven agents with diffusion model-based agents.<n>Our framework outperforms existing methods in prediction accuracy, validating the effectiveness of its modular design.
  arXiv  Detail & Related papers  (2025-10-18T06:23:22Z)
• What Makes LLM Agent Simulations Useful for Policy? Insights From an Iterative Design Engagement in Emergency Preparedness [19.98298738980743]
  There is growing interest in using Large Language Models as agents (LLM agents) for social simulations to inform policy, yet real-world adoption remains limited.<n>This paper addresses the question: How can LLM agent simulations be made genuinely useful for policy?<n>We iteratively developed a system of 13,000 LLM agents that simulate crowd movement and communication during a large-scale gathering under various emergency scenarios.
  arXiv  Detail & Related papers  (2025-09-26T04:51:34Z)
• ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction [84.90394416593624]
  Agentic task-solving with Large Language Models (LLMs) requires multi-turn, multi-step interactions.<n>Existing simulation-based data generation methods rely heavily on costly autoregressive interactions between multiple agents.<n>We propose a novel Non-Autoregressive Iterative Generation framework, called ToolACE-MT, for constructing high-quality multi-turn agentic dialogues.
  arXiv  Detail & Related papers  (2025-08-18T07:38:23Z)
• Simulation Agent: A Framework for Integrating Simulation and Large Language Models for Enhanced Decision-Making [0.7499722271664147]
  Large language models (LLMs) provide intuitive, language-based interactions but can lack the structured, causal understanding required to reliably model complex real-world dynamics.<n>We introduce our simulation agent framework, a novel approach that integrates the strengths of both simulation models and LLMs.
  arXiv  Detail & Related papers  (2025-05-19T22:27:18Z)
• Simulation Streams: A Programming Paradigm for Controlling Large Language Models and Building Complex Systems with Generative AI [3.3126968968429407]
  Simulation Streams is a programming paradigm designed to efficiently control and leverage Large Language Models (LLMs)<n>Our primary goal is to create a framework that harnesses the agentic abilities of LLMs while addressing their limitations in maintaining consistency.
  arXiv  Detail & Related papers  (2025-01-30T16:38:03Z)
• GenSim: A General Social Simulation Platform with Large Language Model based Agents [111.00666003559324]
  We propose a novel large language model (LLMs)-based simulation platform called textitGenSim.<n>Our platform supports one hundred thousand agents to better simulate large-scale populations in real-world contexts.<n>To our knowledge, GenSim represents an initial step toward a general, large-scale, and correctable social simulation platform.
  arXiv  Detail & Related papers  (2024-10-06T05:02:23Z)
• LangSuitE: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments [70.91258869156353]
  We introduce LangSuitE, a versatile and simulation-free testbed featuring 6 representative embodied tasks in textual embodied worlds. Compared with previous LLM-based testbeds, LangSuitE offers adaptability to diverse environments without multiple simulation engines. We devise a novel chain-of-thought (CoT) schema, EmMem, which summarizes embodied states w.r.t. history information.
  arXiv  Detail & Related papers  (2024-06-24T03:36:29Z)
• Ask-before-Plan: Proactive Language Agents for Real-World Planning [68.08024918064503]
  Proactive Agent Planning requires language agents to predict clarification needs based on user-agent conversation and agent-environment interaction. We propose a novel multi-agent framework, Clarification-Execution-Planning (textttCEP), which consists of three agents specialized in clarification, execution, and planning.
  arXiv  Detail & Related papers  (2024-06-18T14:07:28Z)
• TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors [74.67698916175614]
  We propose TrafficSim, a multi-agent behavior model for realistic traffic simulation. In particular, we leverage an implicit latent variable model to parameterize a joint actor policy. We show TrafficSim generates significantly more realistic and diverse traffic scenarios as compared to a diverse set of baselines.
  arXiv  Detail & Related papers  (2021-01-17T00:29:30Z)

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.