# Decoupled Intelligence: A Multi-Agent LLM Framework for Controllable Traffic Scenario Generation in SUMO

arXiv: https://arxiv.org/abs/2605.27685 · HTML: https://mlsanity.com/paper/2605.27685/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 26 May 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 18 of 18)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents](https://mlsanity.com/paper/2306.03314/) (2023)
- [Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies](https://mlsanity.com/paper/2502.02533/) (2025)
- [ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles](https://mlsanity.com/paper/2405.14062/) (2024)
- [TrafficGPT: Viewing, Processing and Interacting with Traffic Foundation Models](https://mlsanity.com/paper/2309.06719/) (2023)
- [ChatSUMO: Large Language Model for Automating Traffic Scenario Generation in Simulation of Urban MObility](https://mlsanity.com/paper/2409.09040/) (2024)
- [SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Model](https://mlsanity.com/paper/2506.21976/) (2025)
- [AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework](https://mlsanity.com/paper/2507.13729/) (2025)
- [Controllable Traffic Simulation through LLM-Guided Hierarchical Reasoning and Refinement](https://mlsanity.com/paper/2409.15135/) (2024)
- [SUMO-MCP: Leveraging the Model Context Protocol for Autonomous Traffic Simulation and Optimization](https://mlsanity.com/paper/2506.03548/) (2025)
- [AgentSUMO: An Agentic Framework for Interactive Simulation Scenario Generation in SUMO via Large Language Models](https://mlsanity.com/paper/2511.06804/) (2025)
- [TrafficSimAgent: A Hierarchical Agent Framework for Autonomous Traffic Simulation with MCP Control](https://mlsanity.com/paper/2512.20996/) (2025)

## Abstract (arXiv)

The integration of Large Language Models (LLMs) with microscopic traffic simulation offers a promising path toward autonomous urban planning and intelligent transportation analysis. However, existing monolithic agent architectures often struggle with the complexity of end-to-end simulation workflows, leading to reasoning failures, parameter inconsistency, and a lack of systematic state management. This paper proposes a novel multi-agent collaborative framework designed to automate the entire lifecycle of traffic simulation in SUMO (Simulation of Urban Mobility). Our approach decouples the simulation pipeline into specialized roles, including Planner, Builder, Demand, Runner, and Analyst, coordinated by a high-level reasoning engine. We introduce a state-persistent Orchestrator leveraging the Model Context Protocol (MCP) to ensure seamless data handover and environmental consistency across distributed agent actions. This architecture enables a robust closed-loop refinement process, where simulation outcomes are iteratively analyzed and optimized to satisfy user-defined Key Performance Indicators (KPIs). Experimental results through role ablation studies demonstrate that the proposed multi-agent framework significantly enhances task success rates and parameter accuracy compared to single-agent baselines. Furthermore, case studies on real-world network extraction and traffic optimization highlight the system's capability to bridge the gap between high-level natural language intent and low-level simulation execution.