Orchestrating Reasoning and Reaction: An Asynchronous Hierarchical Framework for LLM-driven Traffic Signal Control

Explainable Reinforcement Learning for Adaptive Traffic Signal Control

Reinforcement Learning (RL) has emerged as a powerful paradigm for adaptive traffic signal control. However, in safety-critical infrastructure like traffic control, the opaque, black-box nature of deep RL models poses challenges for transportation agency acceptance, regulatory compliance, operational trust, troubleshooting, and fine-tuning. To bridge this gap between high-performance optimization and human-comprehensible interpretability, this effort introduces a novel, explainable entity centric RL framework for safe and transparent traffic signal control. Rather than processing traffic states through monolithic, flat vectors, the proposed architecture disaggregates real-time intersection observations into distinct, high-dimensional lane entities and phase temporal configurations to inherently preserve the structural topology and geometric configurations of the intersection. Relational dependencies and inter-lane conflicts are dynamically extracted via a dual-stage attention network featuring sequential multi-head cross-attention and self-attention blocks. This design yields a real time affinity matrix that quantifies the direct influence of signal phases on specific approach volumes and queues, providing full visual and analytical interpretability. To ensure strict operational reliability, a deterministic action-masking interface is integrated directly into the Proximal Policy Optimization pipeline, explicitly blocking invalid phase transitions to guarantee absolute compliance with established signal timing and safety constraints. Evaluated in a microscopic simulation environment, outperforms state-of-the-art baselines in delay minimization. More importantly, the emergent attention weights align precisely with established traffic engineering principles, offering an auditable, trust-enabling, and deployable architecture for next-generation adaptive traffic control systems.

A Decentralized Traffic Signal Control Framework Using Multiagent Reinforcement Learning With Real-World Operational Constraints

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

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, is proposed.

Spatiotemporal Resource Orchestration for LLM Inference in Vehicular-Edge Networks

Large Language Models (LLMs) have been increasingly applied to intelligent vehicular systems for tasks such as scene understanding, intent reasoning, and natural language interaction. However, their inference demands exceed onboard processing capabilities, making low-latency on-vehicle inference impractical. Although edge computing can partially offload computation, the prolonged nature of LLM inference often causes execution to exceed the residence time of vehicles within edge coverage areas, leading to frequent service interruption. To address these challenges, we propose a collaborative spatiotemporal resource orchestration architecture for LLM inference in vehicular-edge networks (CoInfer). CoInfer exploits the intrinsic decomposability of LLM inference by modeling each request as a Directed Acyclic Graph (DAG) of interdependent subtasks, which are then scheduled, migrated, and aggregated along the road network to preserve end-to-end inference continuity. To improve latency and resource efficiency, CoInfer integrates multi-agent reinforcement learning for coarse-grained task orchestration with a reactive scheduler for fine-grained resource adaptation, forming a closed-loop service optimization under dynamic resource conditions. The simulation results demonstrate that CoInfer achieves a task success ratio of up to 96.0% and reduces the end-to-end inference latency by 35.7% compared to representative baselines.

Human centered artificial intelligence for smart city traffic coordination

A human-centric edge intelligence framework that integrates federated reinforcement learning (FRL) with interpretable human–machine interfaces for urban traffic coordination and provides a practical pathway for evaluating intelligent mobility systems that balance decentralized optimization, privacy preservation, interpretability, scalability, and human-aligned operation is proposed.

A Hierarchical Reinforcement Learning Framework with Spatial-Temporal Graph Attention for Autonomous Driving Decision-Making and Control

This paper presents a hierarchical framework that integrates spatial-temporal graph attention network (ST-GAT) with reinforcement learning for decision and control of autonomous driving. Inspired by the principles of human cognition, the framework decomposes the driving task into two complementary levels: a high-level trajectory planning module that utilizes the soft actor-critic (SAC) algorithm within the Frenet coordinate system, and a low-level tracking control module based on the worst-case soft actor-critic (WCSAC) strategy. This hierarchical decomposition improves policy stability and sample efficiency by decoupling strategic trajectory planning from reactive control execution. Unlike previous methods, the proposed ST-GAT module enables explicit scene understanding by modeling surrounding vehicles and their interactions as a spatial-temporal graph structure. Through attention-based aggregation, the system dynamically captures road geometry and agent behaviors directly from online sensor observations, enabling mapless situational reasoning. Experimental results show that the proposed framework achieves success rates of 92.33% and 97.00% in the roundabout and five-way intersection scenarios in the CARLA simulator.