Large language model (LLM)-based agents are envisioned as cornerstones for autonomous, zero-touch 6G AI-RAN operations. Numerous frameworks adopt LLM-based agents as decision-makers to optimize network configurations, orchestrate resources, and interact with users and connected use cases. However, intrinsic limitations (hallucinations, misaligned human values) and extrinsic adversarial threats (jail-breaks, prompt injections) pose critical risks to network safety, reliability, and privacy—challenges largely overlooked in existing literature. This paper addresses this gap by reviewing state-of-the-art guardrail techniques for 6G AI-RAN. We categorize guardrails across model-level and agent-level layers and map them to common agent application patterns in 6G networks, providing practical foundations for designing trustworthy agentic decision-making frameworks in future 6G AI-RAN systems.

Efficient orchestration of AI services in 6G AI-RAN requires well-structured, ready-to-deploy AI service repositories combined with orchestration methods adaptive to diverse runtime contexts across radio access, edge, and cloud layers. Current literature lacks comprehensive frameworks for constructing such repositories and the proposed orchestrators generally over-simplify key orchestration factors compared to real edge computing environments. To fill these gaps, this paper systematically reviews and categorizes critical attributes influencing AI service orchestration in 6G AI-RAN and introduces an open-source, LLM-assisted toolchain that automates service packaging, deployment, and runtime profiling. We validate the proposed toolchain through the Cranfield AI Service repository case study, demonstrating significant automation benefits, reduced manual coding efforts by up to 98%, and the necessity of infrastructure-specific profiling, paving the way for more production-ready service orchestration and provisioning frameworks.

As 6G networks evolve to support pervasive AI-driven applications, seamless provisioning of Edge AI services has become increasingly vital. However, current orchestration processes remain fragmented, requiring extensive coordination between AI-powered application developers and the network operators. In this paper, we propose a novel end-to-end orchestration framework that integrates Large Language Model (LLM) agents into O-RAN to automate edge AI service subscription and deployment. Our system translates high-level user intents into orchestrated workflows, including AI model selection, mobility-aware placement, and performance monitoring. We demonstrate the framework via a prototype built on our open-source ORAN simulator, showcasing intelligent, intent-driven AI service provisioning. This work represents a key step toward AI-native, accessible, and scalable service management in 6G.

Mixed-precision computing, a widely applied technique in AI, offers a larger trade-off space between accuracy and efficiency. The recent purposed Mixed-Precision Over-theAir Federated Learning (MP-OTA-FL) enables clients to operate at appropriate precision levels based on their heterogeneous hardware, taking advantages of the larger trade-off space while covering the quantization overheads of the mixed-precision modulation scheme with the OTA aggregation process. A key to further exploring the potential of the MP-OTA-FL framework is the optimization of client precision levels. The choice of precision level hinges on multifaceted factors including hardware capability, potential client contribution, and user satisfaction, among which factors can be difficult to define or quantify.In this paper, we propose a precision planning framework that integrates Retrieval-Augmented Generation (RAG) LLMs and dynamic client profiling to optimize satisfaction and contributions. This includes a hybrid interface for gathering device/user insights and an RAG database storing historical quantization decisions with feedback. Experiments show that our method boosts satisfaction, energy savings, and global model accuracy in MP-OTA-FL systems.

Load balancing in open radio access networks (O-RAN) is critical for ensuring efficient resource utilization, and the user’s experience by evenly distributing network traffic load. Current research mainly focuses on designing load-balancing algorithms to allocate resources while overlooking the cascade stability of load balancing, which is critical to prevent endless handover. The main challenge to analyse the cascade stability lies in the difficulty of establishing an accurate mathematical model to describe the process of load balancing due to its nonlinearity and high-dimensionality. In our previous theoretical work, a simplified general dynamic function was used to analyze the stability. However, it is elusive whether this function is close to the reality of the load balance process. To solve this problem, 1) a data-driven method is proposed to identify the dynamic model of the load balancing process according to the real-time traffic load data collected from the radio units (RUs); 2) the stability condition of load balancing process is established for the identified dynamics model. Based on the identified dynamics model and the stability condition, the RAN Intelligent Controller (RIC) can control RUs to achieve a desired load-balancing state while ensuring cascade stability.

Large-scale scenario databases may contain hundreds of thousands of scenarios for the verification and validation (V&V) of autonomous vehicles (AV). Scenarios in the database are often labelled with semantic Operational Design Domain (ODD) tags (e.g., WeatherRainy, RoadTypeHighway and ActorTypeTruck) to be queried via exact tag matching. Such a scenario database design has two major limitations, i.e. combinatorial scenario generation inevitably leads to many redundant scenarios, and each ODD query matches only a small number of scenarios in the database (0.2% in our case study), rendering most of the database wealth wasted. We propose a novel scenario database design and the first ODD-based query-time scenario mutation framework to address the limitations. Our case study results show that the proposed framework has the potential to fully utilize all the database scenarios at query time while eliminating scenario redundancy in the database (in our case study, given the same ODD query, the number of final matched scenarios increased by 36 times, diversity increased by 99 times, and scenario database utilization rate increased from 0.2% to 36%).

Scenario-based verification and validation (V&V) has emerged as the predominant approach for the performance evaluation of automated driving systems (ADSs). Many scenario-generation methods have been proposed to search for critical scenarios, i.e. disengagement or traffic rule violations. However, the widely adopted binary (pass/fail) criterion suffers from two main limitations, i.e., the difficulty of locating root causes and the lack of statistical guarantee of testing sufficiency. Recently, new scenario engineering approaches focusing on the intelligence of ADSs enlightened a promising pathway via dynamic driving task decomposition and function atom constraints. However, none of the state-of-the-art scenario description languages support such approaches. To fill this gap and facilitate further research into this promising direction, in this work, we propose a generic architecture to extend the existing scenario description languages for the intelligence testing of ADSs. The case study with WMG SDL demonstrates the capability and flexibility of the proposed extension design in defining intelligence function constraints.

It has become a consensus that autonomous vehicles (AVs) will first be widely deployed on highways. However, the complexity of highway interchanges becomes the bottleneck for their deployment. An AV should be sufficiently tested under different highway interchanges, which is still challenging due to the lack of available datasets containing diverse highway interchanges. In this paper, we propose a model-driven method, Flyover, to generate a dataset of diverse interchanges with measurable diversity coverage. First, Flyover uses a labeled digraph to model interchange topology. Second, Flyover takes real-world interchanges as input to guarantee topology practicality and extracts different topology equivalence classes by classifying corresponding topology models. Third, for each topology class, Flyover identifies the corresponding geometrical features for the ramps and generates concrete interchanges using k-way combinatorial coverage and differential evolution. To illustrate the diversity and applicability of the generated interchange dataset, we test the built-in traffic flow control algorithm in SUMO and the fuel-optimization trajectory tracking algorithm deployed to Alibaba's autonomous trucks on the dataset. The results show that except for the geometrical difference, the interchanges are diverse in throughput and fuel consumption under the traffic flow control and trajectory tracking algorithms, respectively.

This paper presents a scenario-based safety assurance process for Automated Driving Systems (ADSs) combined with the Vehicle-to-Everything (V2X) connectivity aspect, system with connectivity capability is benchmarked with system without such capabilities. In addition, a novel approach to V2X modelling is introduced and implemented to obtain the required configuration of the V2X parameters for individual system, such modelling approach ensures that the V2X is effective within a system during testing by using a distance-based V2X parameter that correlates to the speed of the system. Such parameter is then used as the configuration of the V2X model when carrying out the ADS and V2X combined test. Using a pedestrian crossing scenario, a reduction in failure cases is demonstrated when combining the V2X and the ADS. Therefore, a synchronised approach of vehicle, sensor and communication sub-system can improve the overall safety function of the system.

Autonomous vehicle (AV) systems must be comprehensively tested and evaluated before they can be deployed. High-fidelity simulators such as CARLA or LGSVL allow this to be done safely in very realistic and highly customizable environments. Existing testing approaches, however, fail to test simulated AVs systematically, as they focus on specific scenarios and oracles (e.g., lane following scenario with the “no collision” requirement) and lack any coverage criteria measures. In this paper, we propose$\mathtt {AVUnit}$, a framework for systematically testing AV systems against customizable correctness specifications. Designed modularly to support different simulators,$\mathtt {AVUnit}$consists of two new languages for specifying dynamic properties of scenes (e.g. changing pedestrian behaviour after waypoints) and fine-grained assertions about the AV's journey.$\mathtt {AVUnit}$further supports multiple fuzzing algorithms that automatically search for test cases that violate these assertions, using robustness and coverage measures as fitness metrics. We evaluated the implementation of$\mathtt {AVUnit}$for the LGSVL+Apollo simulation environment, finding 19 kinds of issues in Apollo, which indicate that the open-source Apollo does not perform well in complex intersections and lane-changing related scenarios.

Autonomous vehicles (AVs) play an important role in transforming our transportation systems and relieving traffic congestion. To guarantee their safety, AVs must be sufficiently tested before they are deployed to public roads. Existing testing often focuses on AVs’ collision avoidance on a given route. There is little work on the systematic testing for AVs’ route planning and tracking on a map. In this paper, we propose CROUTE, a novel testing method based on a new AV testing criterion called route coverage. First, the map is modeled as a labeled Petri net, where roads, junctions, and traffic signs are modeled as places, transitions, and labels, respectively. Second, based on the Petri net, we define junctions’ topology features and route features for junction classification. The topology feature describes the topology of roads forming the junction, and the route feature identifies the actions that a vehicle can take to follow a route. They can characterize route types on a map. Hence, route coverage measures how many route types are covered. We then propose a systematic method that aims to cover all route types for a well-designed AV system with a small number of test cases. We implement and evaluate CROUTE on Baidu Apollo running with the LGSVL simulator. We carry out testing on the map from a section of San Francisco and find six different types of issues in Apollo. The experiment results show the validity of route coverage and the efficiency of CROUTE.

Collision avoidance is one of the crucial functions of autonomous driving systems (ADSs) to guarantee the safety of autonomous vehicles (AVs). It requires extensive testing before an AV is deployed to public roads. Most of the current ADS testing methods generate test cases either from real traffic data or manually designed for some specific scenarios. There is little work on systematic methods to generate test cases from a complete map where an AV operates. Systematic testing on such a map is challenging due to the enormous scenarios. In this paper, we propose a collision-avoidance testing method for ADSs running on a map, which aims to reduce the scenario space while maintaining scenario diversity. The method consists of test case classification and test case generation. First, we build the topology structure of a map, based on which we classify possible scenarios into different classes. Second, we divide test cases into different classes using the topology-based scenario classification and fuzzy number-based motion evaluation. Third, we implement a bisection method to generate test cases that can efficiently expose ADSs' failures. We evaluate our method on one of the state-of-the-art ADSs, Baidu Apollo. The experiment results show that our method discovers Apollo's issues effectively while reducing the number of generated test cases by 77.36%, compared with the random method.

Autonomous Driving Systems (ADSs), which replace humans to drive vehicles, are complex software systems deployed in autonomous vehicles (AVs). Since the execution of ADSs highly relies on maps, it is essential to perform global map-based testing for ADSs to guarantee their correctness and AVs’ safety in different situations. Existing methods focus more on specific scenarios rather than global testing throughout the map. Testing on a global map is challenging since the complex lane connections in a map can generate enormous scenarios. In this work, we propose ATLAS, an approach to ADSs’ collision avoidance testing using map topology-based scenario classification. The core insight of ATLAS is to generate diverse testing scenarios by classifying junction lanes according to their topology-based interaction patterns. First, ATLAS divides the junction lanes into different classes such that an ADS can execute similar collision avoidance maneuvers on the lanes in the same class. Second, for each class, ATLAS selects one junction lane to construct the testing scenario and generate test cases using a genetic algorithm. Finally, we implement and evaluate ATLAS on Baidu Apollo with the LGSVL simulator on the San Francisco map. Results show that ATLAS exposes nine types of real issues in Apollo 6.0 and reduces the number of junction lanes for testing by 98%.