SimTIO: A Simulation-Grounded Multi-Agent LLM Framework for Compositional Traffic Intervention Optimization

Shuyang Li; Ruimin Ke

cs.MASep 4, 2026

SimTIO: A Simulation-Grounded Multi-Agent LLM Framework for Compositional Traffic Intervention Optimization

Authors: Shuyang Li, Ruimin Ke

Organizations: Civil and Environmental Engineering, Rensselaer Polytechnic Institute Troy, New York, 12180

Abstract

Traffic analysts must translate diagnosed bottlenecks into executable interventions without allowing local improvements to degrade network-wide performance. This study presents SimTIO, a simulation-grounded multi-agent large language model framework for composing and selecting traffic interventions under explicit operational constraints. SimTIO first simulates an unmodified SUMO scenario to identify a baseline-frozen set of ten bottleneck edges. A grounded sampler then initializes signal-control, corridor-speed, and demand-preserving routing actions, while three specialist agents use measured simulation feedback to select one-parameter refinements from validator-confirmed mutation catalogs. Compatible actions are combined and re-simulated so that their interaction effects are measured rather than inferred. Final selection minimizes bottleneck time loss while constraining network-wide delay, neighboring-road spillover, throughput loss, and teleport events, with the unmodified scenario retained as a no-operation guard. Across 15 cases covering five U.S. urban networks, three synthetic-demand seeds, and 2,400 origin-destination trips per scenario, SimTIO reduced Top-10 bottleneck time loss by an average of 9.18 percent and network-wide delay by 2.78 percent. It found a feasible improving plan in 86.7 percent of cases, compared with 73.3 percent for grounded random search and 80.0 percent for a deterministic heuristic under the same seven-simulation budget, although the differences in Top-10 improvement were not statistically significant. These results support using LLMs as constrained, feedback-guided local search operators while reserving final decision authority for executable tools, microscopic simulation, and explicit safety constraints.

Figures & tables

Figure 1: Simulation-grounded multi-agent traffic optimization framework. Grounded sampling initializes diverse interventions; specialist LLM agents refine measured parents, after which compatible actions may be composed before constrained final selection.

Figure 2: Intervention mechanisms supported by the optimizer: fixed-time signal green-split adjustment, corridor-level speed control, and partial rerouting around a diagnosed bottleneck. Grounded initialization selects the initial targets and parameters, while an LLM feedback specialist selects a validator-confirmed one-parameter refinement. Deterministic utilities apply the corresponding SUMO modifications.

City	Edges	Junctions	TLS	Trips	Delay (s)
Albany	6,193	4,309	107	2,400	$112.80\pm 0.26$
Troy	6,107	4,355	57	2,400	$99.79\pm 0.84$
Ann Arbor	10,151	7,522	81	2,400	$138.58\pm 3.13$
Los Angeles	6,969	4,954	172	2,400	$175.76\pm 1.26$
Manhattan	5,993	4,065	256	2,400	$245.31\pm 13.03$

Table 1: Equal-demand SUMO scenarios. Delay is baseline mean vehicle time loss, reported as mean

\pm

sample standard deviation across three seeds.

Component	Setting
Network source	Five urban road networks derived from OpenStreetMap data (© OpenStreetMap contributors).
LLM	OpenAI Chat Completions API; gpt-5.6-luna ; model-default sampling; JSON response mode; 500 output tokens; 60-s timeout and at most two retries after the initial request, including one structured repair attempt for an invalid catalog selection.
Search budget	At most seven candidate SUMO evaluations per case. LLM search uses three grounded initial proposals, up to two feedback mutations, and up to two compatible bundles; each baseline uses five proposals and up to two bundles.
Candidate space	Signal timing, five-edge corridor speed control, single-edge rerouting, and validated topology actions. Numeric choices are discrete, and Top-10 ranking excludes edge fragments shorter than 10 m.
Signal timing	Fixed-time cycle and green-split plans derived using Webster’s method; original phase states and yellow/all-red transition intervals are preserved.
SUMO	Version 1.27.1; 1-s step; complete execution until all vehicles arrive; trip-level statistics and emissions plus 60-s edge measurements.

Table 2: Reproducibility settings for the main comparison.

Method	Valid (%)	Success (%)	Best nets.	Sim. eff. (%)	Top-10 (%)	Global (%)
LLM feedback	100.0	86.7	3/5	35.1	9.18	2.78
Grounded random	100.0	73.3	1/5	34.0	9.00	3.03
Heuristic	97.3	80.0	1/5	39.0	9.60	2.69

Table 3: Budget-matched proposal-source comparison over five networks and three demand seeds. Success denotes a feasible selected plan with at least 1% Top-10 reduction.

Figure 3: Proposal-source comparison over three demand seeds. Bars in (a) show mean Top-10 reduction and sample-standard-deviation error bars. Panel (b) reports case-level optimization success and candidate-level simulation efficiency under the common seven-evaluation cap.

Network	Top-10 (%)	Global delay (%)	Sim. eff. (%)	Success
Albany	2.25 $\pm$ 2.11	0.17 $\pm$ 0.52	21.1	2/3
Troy	8.55 $\pm$ 11.17	0.75 $\pm$ 1.27	28.6	2/3
Ann Arbor	8.25 $\pm$ 5.83	1.75 $\pm$ 0.46	30.0	3/3
Los Angeles	5.58 $\pm$ 6.84	0.51 $\pm$ 1.28	31.6	3/3
Manhattan	21.27 $\pm$ 14.23	10.71 $\pm$ 7.55	66.7	3/3
Overall	9.18 $\pm$ 10.18	2.78 $\pm$ 5.08	35.1	13/15

Table 4: Five-network performance of the LLM-feedback optimizer over three demand seeds. Reductions are mean

\pm

sample standard deviation in percentage points and include no-op outcomes.

Figure 4: Search outcomes over 15 city–seed cases. Panel (a) reports the intervention family selected by each proposal source. Panel (b) separates initial, feedback-refined, bundled, and no-op outcomes for the LLM search.

Intelligent Transportation Systems

Intelligent Transportation Systems apply sensing, communication, AI, and optimization to make transport networks safer and more efficient.

See all 301 papers

May 26, 2026

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

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.

Shuyang Li, Ruimin Ke

Civil and Environmental Engineering, School of Engineering, Rensselaer Polytechnic Institute, Troy, United States.

Multi-Agent LLM Systems Intelligent Transportation Systems LLM Agent Orchestration

Ask PDF

Sep 3, 2026

SimSkill: A Self-Evolving LLM Agent for Skill and Knowledge Accumulation in Traffic Simulation

Cumulative culture enables humans to preserve, reuse, and extend knowledge and skills across experiences and generations. Inspired by this principle, we introduce SimSkill, a self-evolving agent built around the Simulation of Urban MObility (SUMO) traffic simulator. SimSkill continually identifies capability gaps, generates and solves environment-grounded tasks, verifies solutions through an action--critic loop, and consolidates experience into episodic, procedural, and semantic memory. Through autonomous exploration, it builds a library of reusable skills and knowledge spanning major stages of the traffic-simulation workflow. We evaluate SimSkill on two held-out benchmarks across three backbone LLMs, with each result independently verified. It improves verified success by up to 25 percentage points, and ablations show complementary contributions from procedural and semantic memory. Its benefits remain backbone- and budget-dependent, as memory does not improve every model or uniformly reduce inference cost. More broadly, SimSkill illustrates a natural-language-centered design paradigm for LLM-based agent systems. Its high-level control logic, operating principles, and accumulated knowledge are expressed in natural language, while an LLM integrates them with executable tools and code to realize precise and reproducible execution. All code and experimental data are publicly available at https://github.com/qiliuchn/SimSkill-V1.

Qi Liu, Qinzheng Wang, Can Li +2

School of Transportation, Jilin University, 5988 Renmin St., Changchun, Jilin 130022, China · Key Laboratory of Road and Traffic Engineering of the Ministry of Education, College of Transportation, Tongji University, 4800 Cao’an Rd., Shanghai 201804, China

Continual Learning for LLM Agents LLM Agent Self-Improvement LLM Agent Skill Learning Memory-Augmented Language Model Agents

Ask PDF

Jul 17, 2026

HiLLTS: Zero-Shot Hierarchical LLM-Guided Traffic Signal Control for Sustainable Transportation

Urban traffic congestion significantly increases fuel consumption, greenhouse gas emissions, and commuter delays, resulting in substantial economic losses and environmental harm in modern cities. Traditional traffic signal control strategies such as fixed-time scheduling, actuated control, and reinforcement learning (RL)-based methods, offer different degrees of adaptability; however, RL-based methods can require extensive retraining, careful reward design, and substantial simulation data when transferred across networks or demand regimes. To address these challenges, we propose HiLLTS, an LLM-guided traffic signal control framework that employs a hierarchical three-layer architecture consisting of a central coordination agent, a district layer and multiple cluster-level intersection agents. Experimental results demonstrate consistent improvements in both congestion and environmental performance. Compared with the strongest non-LLM baseline in each scenario, HiLLTS reduces average waiting time by 36.73% under the low-congestion scenario and 14.71% under the high-congestion scenario, while reducing average CO2 emissions by 7.87% and 8.57%, respectively. Larger gains are observed against weaker baselines: under low congestion, HiLLTS achieves reductions of up to 18.00% in emissions and 62.07% in waiting time relative to Fixed-Time control; under high congestion, reductions of up to 28.89% in emissions and 40.36% in waiting time are observed relative to Max Pressure. The ablation study further validates the contribution of LLM-guided coordination over rule-based control

Yue Ding, Tendai Mukande, Mingming Liu

Research Ireland Centre for Researching Training in Machine Learning at Dublin City University

Language Model-Based Control Intelligent Transportation Systems Multi-Agent Control Traffic Signal Control

Ask PDF

Abstract

Intelligent Transportation Systems

Explore similar work

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

SimSkill: A Self-Evolving LLM Agent for Skill and Knowledge Accumulation in Traffic Simulation

HiLLTS: Zero-Shot Hierarchical LLM-Guided Traffic Signal Control for Sustainable Transportation