TrafficSimAgent: A Hierarchical Agent Framework for Autonomous Traffic Simulation with MCP Control

2025-12-24

AI Summary

Non-expert users face significant challenges in efficiently utilizing traffic simulation platforms such as SUMO. Method: This paper proposes an LLM-driven hierarchical agent framework featuring a novel two-tier expert collaboration mechanism—comprising high-level strategic and low-level operational agents—integrated with an MCP-compatible tool-calling architecture. The framework enables natural language instruction interpretation, automated experimental workflow planning, and real-time traffic decision-making. It addresses key technical challenges including robust parsing of ambiguous instructions and closed-loop autonomous optimization of traffic policies. Results: Extensive multi-scenario experiments demonstrate stable simulation execution and generation of semantically appropriate strategies for ambiguous inputs. Compared to state-of-the-art LLM-based approaches and conventional systems, the framework achieves significantly higher experimental success rates and policy rationality, thereby substantially lowering the barrier to entry for traffic simulation experimentation.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Sampling/Simulation-based Search
• Multiagent Systems: Agent Communication

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Traffic simulation is important for transportation optimization and policy making. While existing simulators such as SUMO and MATSim offer fully-featured platforms and utilities, users without too much knowledge about these platforms often face significant challenges when conducting experiments from scratch and applying them to their daily work. To solve this challenge, we propose TrafficSimAgent, an LLM-based agent framework that serves as an expert in experiment design and decision optimization for general-purpose traffic simulation tasks. The framework facilitates execution through cross-level collaboration among expert agents: high-level expert agents comprehend natural language instructions with high flexibility, plan the overall experiment workflow, and invoke corresponding MCP-compatible tools on demand; meanwhile, low-level expert agents select optimal action plans for fundamental elements based on real-time traffic conditions. Extensive experiments across multiple scenarios show that TrafficSimAgent effectively executes simulations under various conditions and consistently produces reasonable outcomes even when user instructions are ambiguous. Besides, the carefully designed expert-level autonomous decision-driven optimization in TrafficSimAgent yields superior performance when compared with other systems and SOTA LLM based methods.

Problem

• Enables non-experts to conduct traffic simulations easily
• Optimizes experiment design and decision-making in simulations
• Handles ambiguous user instructions for robust simulation outcomes

Innovation

• LLM-based hierarchical agent framework for traffic simulation
• High-level agents plan workflows using natural language instructions
• Low-level agents optimize actions based on real-time conditions