TrafficClaw: Generalizable Urban Traffic Control via Unified Physical Environment Modeling

• URL: http://arxiv.org/abs/2604.17456v1
• Date: Sun, 19 Apr 2026 14:17:56 GMT
• Title: TrafficClaw: Generalizable Urban Traffic Control via Unified Physical Environment Modeling
• Abstract summary: TrafficClaw is a framework for general urban traffic control built upon a unified runtime environment.<n>We develop an agent with executable reasoning and reusable procedural memory, supporting unified diagnostics across subsystems.<n>Experiments demonstrate that TrafficClaw achieves robust, transferable, and system-aware performance across unseen traffic scenarios, dynamics, and task configurations.
• Score: 15.57539332792164
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Urban traffic control is a system-level coordination problem spanning heterogeneous subsystems, including traffic signals, freeways, public transit, and taxi services. Existing optimization-based, reinforcement learning (RL), and emerging LLM-based approaches are largely designed for isolated tasks, limiting both cross-task generalization and the ability to capture coupled physical dynamics across subsystems. We argue that effective system-level control requires a unified physical environment in which subsystems share infrastructure, mobility demand, and spatiotemporal constraints, allowing local interventions to propagate through the network. To this end, we propose TrafficClaw, a framework for general urban traffic control built upon a unified runtime environment. TrafficClaw integrates heterogeneous subsystems into a shared dynamical system, enabling explicit modeling of cross-subsystem interactions and closed-loop agent-environment feedback. Within this environment, we develop an LLM agent with executable spatiotemporal reasoning and reusable procedural memory, supporting unified diagnostics across subsystems and continual strategy refinement. Furthermore, we introduce a multi-stage training pipeline with supervised initialization and agentic RL with system-level optimization, further enabling coordinated and system-aware performance. Experiments demonstrate that TrafficClaw achieves robust, transferable, and system-aware performance across unseen traffic scenarios, dynamics, and task configurations. Our project is available at https://github.com/usail-hkust/TrafficClaw.

Related papers

• CROSS: A Mixture-of-Experts Reinforcement Learning Framework for Generalizable Large-Scale Traffic Signal Control [11.628278541732513]
  We propose CROSS, a novel Mixture-of-Experts (MoE)-based decentralized RL framework for generalizable adaptive traffic signal control (ATSC)<n>We first introduce a Predictive Contrastive Clustering (PCC) module that forecasts short-term state transitions to identify latent traffic patterns, followed by clustering and contrastive learning to enhance pattern-level representation.<n>We further design a Scenario-Adaptive MoE module that augments a shared policy with multiple experts, thus enabling adaptive specialization and more flexible scenario-specific strategies.
  arXiv  Detail & Related papers  (2026-03-26T01:48:15Z)
• CoordLight: Learning Decentralized Coordination for Network-Wide Traffic Signal Control [15.468107943726617]
  CoordLight is a framework designed to improve intra-neighborhood traffic by enhancing decision-making at individual junctions (agents)<n>We propose an advanced MARL algorithm, named Neighbor-aware Policy Optimization (NAPO), which integrates an attention mechanism that discerns the state and action dependencies among adjacent agents.<n>We empirically show that CoordLight consistently exhibits superior performance across diverse traffic networks with varying traffic flows.
  arXiv  Detail & Related papers  (2026-03-25T14:46:31Z)
• Robust Single-Agent Reinforcement Learning for Regional Traffic Signal Control Under Demand Fluctuations [5.784337914162491]
  Traffic congestion, primarily driven by intersection queuing, significantly impacts urban living standards, safety, environmental quality, and economic efficiency.<n>This study introduces a novel single-agent reinforcement learning framework for regional adaptive TSC.<n>The framework exhibits robust anti-fluctuation capability and significantly reduces queue lengths.
  arXiv  Detail & Related papers  (2025-11-01T13:18:50Z)
• Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmap [51.198001060683296]
  Large Language Models (LLMs) offer transformative potential to address transportation challenges.<n>This survey first presents LLM4TR, a novel conceptual framework that systematically categorizes the roles of LLMs in transportation.<n>For each role, our review spans diverse applications, from traffic prediction and autonomous driving to safety analytics and urban mobility optimization.
  arXiv  Detail & Related papers  (2025-03-27T11:56:27Z)
• CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Control [7.0964925117958515]
  Traffic Signal Control (TSC) plays a critical role in urban traffic management by optimizing traffic flow and mitigating congestion.<n>Existing approaches fail to address the essential need for inter-agent coordination.<n>We propose CoLLMLight, a cooperative LLM agent framework for TSC.
  arXiv  Detail & Related papers  (2025-03-14T15:40:39Z)
• Navigating Motion Agents in Dynamic and Cluttered Environments through LLM Reasoning [69.5875073447454]
  This paper advances motion agents empowered by large language models (LLMs) toward autonomous navigation in dynamic and cluttered environments.<n>Our training-free framework supports multi-agent coordination, closed-loop replanning, and dynamic obstacle avoidance without retraining or fine-tuning.
  arXiv  Detail & Related papers  (2025-03-10T13:39:09Z)
• LLM-Assisted Light: Leveraging Large Language Model Capabilities for Human-Mimetic Traffic Signal Control in Complex Urban Environments [3.7788636451616697]
  This work introduces an innovative approach that integrates Large Language Models into traffic signal control systems. A hybrid framework that augments LLMs with a suite of perception and decision-making tools is proposed. The findings from our simulations attest to the system's adeptness in adjusting to a multiplicity of traffic environments.
  arXiv  Detail & Related papers  (2024-03-13T08:41:55Z)
• A Holistic Framework Towards Vision-based Traffic Signal Control with Microscopic Simulation [53.39174966020085]
  Traffic signal control (TSC) is crucial for reducing traffic congestion that leads to smoother traffic flow, reduced idling time, and mitigated CO2 emissions. In this study, we explore the computer vision approach for TSC that modulates on-road traffic flows through visual observation. We introduce a holistic traffic simulation framework called TrafficDojo towards vision-based TSC and its benchmarking.
  arXiv  Detail & Related papers  (2024-03-11T16:42:29Z)
• Adaptive Hierarchical SpatioTemporal Network for Traffic Forecasting [70.66710698485745]
  We propose an Adaptive Hierarchical SpatioTemporal Network (AHSTN) to promote traffic forecasting. AHSTN exploits the spatial hierarchy and modeling multi-scale spatial correlations. Experiments on two real-world datasets show that AHSTN achieves better performance over several strong baselines.
  arXiv  Detail & Related papers  (2023-06-15T14:50:27Z)
• AI-aided Traffic Control Scheme for M2M Communications in the Internet of Vehicles [61.21359293642559]
  The dynamics of traffic and the heterogeneous requirements of different IoV applications are not considered in most existing studies. We consider a hybrid traffic control scheme and use proximal policy optimization (PPO) method to tackle it.
  arXiv  Detail & Related papers  (2022-03-05T10:54:05Z)
• End-to-End Intersection Handling using Multi-Agent Deep Reinforcement Learning [63.56464608571663]
  Navigating through intersections is one of the main challenging tasks for an autonomous vehicle. In this work, we focus on the implementation of a system able to navigate through intersections where only traffic signs are provided. We propose a multi-agent system using a continuous, model-free Deep Reinforcement Learning algorithm used to train a neural network for predicting both the acceleration and the steering angle at each time step.
  arXiv  Detail & Related papers  (2021-04-28T07:54:40Z)
• MetaVIM: Meta Variationally Intrinsic Motivated Reinforcement Learning for Decentralized Traffic Signal Control [54.162449208797334]
  Traffic signal control aims to coordinate traffic signals across intersections to improve the traffic efficiency of a district or a city. Deep reinforcement learning (RL) has been applied to traffic signal control recently and demonstrated promising performance where each traffic signal is regarded as an agent. We propose a novel Meta Variationally Intrinsic Motivated (MetaVIM) RL method to learn the decentralized policy for each intersection that considers neighbor information in a latent way.
  arXiv  Detail & Related papers  (2021-01-04T03:06:08Z)

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.