cs.ROOct 22, 2026

LAST-V2X: Language-Driven Adaptive Scenario Synthesis and Testing for Communication-Induced Failures in V2X Safety Applications

Authors: Keshu Wu, Hao Zhang, Rui Gan, Pei Li, Jiwan Jiang, Yang Zhou

Organizations: Texas A&M University · University of Wisconsin-Madison · University of Wyoming

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Vehicle-to-everything (V2X) communication enables connected vehicles to make safety-critical decisions, but delayed, missing, or incorrect information can compromise driving safety. Systematically testing such failures is challenging because traffic interactions, communication conditions, and application responses must be jointly configured to produce meaningful scenarios. This paper presents LAST-V2X, a language-driven, adaptive framework for automated scenario synthesis and safety testing of V2X applications. LAST-V2X leverages large language models (LLMs) to translate natural-language test descriptions into executable scenarios grounded in roadway geometry, V2X communication semantics, and vehicle behavior. The framework integrates physical traffic simulation with spatially aware communication modeling and message-level fault injection to evaluate how information degradation affects vehicle decisions. To establish whether an observed safety failure is caused by communication rather than the underlying traffic conditions, LAST-V2X employs matched executions under degraded and ground-truth information. Furthermore, an execution-guided refinement mechanism combines parameter search and LLM self-reflection to identify ineffective test configurations, improve scenario effectiveness, and produce minimal reproducible failure cases. Experiments across diverse CARLA environments and V2X safety applications demonstrate the framework's ability to generate reliable scenarios, distinguish communication-induced failures from unrelated safety violations, and substantially improve failure discovery through adaptive refinement. These results establish LAST-V2X as a systematic approach to language-driven, causally verified, and adaptive safety testing for connected vehicle systems.

Figures & tables

Figure 1
Figure 1: Overview of LAST-V2X . LLM Agent Analysis verifies the intent; Retrieval-Augmented Scenario Grounding places it on a feasible junction; Automated V2X Scenario Synthesis runs it in CARLA with faulted messages beside a ground-truth ego; Scenario Refinement admits a failure only if the message-driven ego alone fails, else refines it.
   Age budget (s)Position
ApplicationFull nameFunctionSPaTBSMerror (m)
Signal applications infrastructure-to-vehicle (SPaT/MAP)
RLVWRed-Light Violation WarningWarns against entering on red1.0––
GLOSAGreen Light Optimal Speed AdvisoryRecommends speed for a green arrival1.0––
Conflict applications vehicle-to-vehicle (BSM)
IMAIntersection Movement AssistWarns of crossing-vehicle conflicts–0.51.5
Table 1: V2X safety applications and their message requirements (SAE J2945/1 [ 65 ] ). Age budgets bound the staleness of the consumed SPaT or BSM stream; “–” marks a quantity the application does not use.
Figure 2: 100 generated scenes. a , Application and town. b , Driving quality (RF, route following; ACC, acceleration; YV, yaw rate; LI, lane invasion; CE, communication exposure). c , Scene conditions. d , Minimum gap. e , Examples.
Figure 3: A nine-agent left turn in Town03 under a healthy channel. a , Prompt and compiled specification. b , Six instants from four viewpoints. c , Agent paths and V2I range. d , True and estimated signal phases. e , Message deliveries.
Figure 4: Corridor traversal along an RSU chain. a , Shared prompt; CC is the condition-specific clause. b , Clause, parsed value, and 10-seed results per condition, relative to No V2X. c , Camera frames on the retrieved corridor. d , Junctions with known SPaT. e , f , Ego speed without and with traffic.
Figure 5: Multi-CV cooperation: EEBL relay chain (a–d) and IMA mutual yield (e–h). a , e , Prompts. b , f , Retrieved scenes. c , CV3 speed and gap. g , Distance between the crossing vehicles. d , h , Clause, CARLA frame, and 10-seed results per condition.
Figure 6: Scenario refinement on the 50-scene fault suite. a , Outcome by fault class. b , Executions or prompt revisions to first admission. c , Median best margin during search (shaded: IQR).
Figure 7: Refinement example rlvw_late_freeze . a , Prompt revisions by LLM self-reflection. b , c , Paired runs of the original and revised prompts: ego and ground-truth twin, true and received signal phases, and CARLA frames.
Component and metric WithWithoutComponent and metric WithWithout
Ground-truth rolloutHeight-aware blockage
Alarms raised (112 live scenes)↓\downarrow160Divergences (15 healthy scenes)↓\downarrow3460
False alarms among them↓\downarrow059In-range coverage, Town10 (%)↑\uparrow100.047.7
Feasibility gateScene planner (multi-approach junctions)
IMA admissions per 150 executions↑\uparrow29.015.3Conflict gap, ground-truth ego (m)↓\downarrow10.849.8
Seeds with zero admissions (of 3)↓\downarrow01Conflict gap, message-driven ego (m)↓\downarrow2.45.7
Table 2: Ablation of LAST-V2X components. Each block removes one component from the full pipeline; ↑\uparrow / ↓\downarrow marks whether a higher or lower value is better, and the better value is in bold.
Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

CheckCondition rejected or flagged
error blocking; returned to the parser for repair
no_effective_faultNo fault can breach any application budget (a vacuous intent); suggestions name k∗k^{\ast} or a freeze/skew fault
anchor_beyond_horizonThe kk -th anchored occurrence, or the ego decision point, falls after the horizon TT
agent_unreachableThe conflict cannot form
no_locusRetrieval returns no locus; the message names the first filter that empties the candidate set
warn executed, but flagged as unlikely to be attributable
Appendix
Table 3: Verifier check families, grouped by severity.
ParameterSymbolValueParameterSymbolValue
Path lossHeight-aware blockage
Transmit powerPtxP_{\mathrm{tx}}0 dBmBuilding loss rateη\eta5 dB/m
Path-loss exponentnn2.0Ray sampling stepΔs\Delta s1 m
Noise floorPfloorP_{\mathrm{floor}}−100-100 dBmRSU antenna heighthRSUh_{\mathrm{RSU}}6.5 m
Communication radiusRR100 m †Receiver antenna heighthOBUh_{\mathrm{OBU}}1.5 m
Latency and deliverySaturation excess heighthsath_{\mathrm{sat}}10 m
Appendix
Table 4: Default channel parameters. † The corridor study varies RR over 50, 100, and 150 m.
OperatorTargetEffectSearch range
Delivery faults
dropanySuppresses the next kk broadcasts in the window (all if kk is unset)k∈[1,40]k\in[1,40]
burst_dropanyGilbert–Elliott burst loss with transitions pgb,pbgp_{\mathrm{gb}},p_{\mathrm{bg}} and a bad-state loss ratepathology library
delayanyConstant delay plus jitter, optionally applied after reception (decode delay)[0.05,5][0.05,5] s
Timestamp fault
skewanyShifts the reported timestamp without delaying delivery, so the receiver misreads the age∣skew∣≤30|\mathrm{skew}|\leq 30 s
Appendix
Table 5: Fault operators, their target streams, and the parameter ranges explored by specification-space search.
App.Decision ruleViolation
Signal applications
RLVWPredicts the phase at arrival; once d≤ds(v)d\leq d_{s}(v) , stops if arrival falls on red, or on yellow after the countdown expires. Holds on a current red within 6 m of the bar; without signal data, stops at the decision pointRed entry
GLOSAKeeps speed if arriving within the current green; otherwise advises v=d/tgreenv=d/t_{\mathrm{green}} , clipped to [3,16][3,16] m/sRed entry
Conflict applications
IMAStops if a crossing track reaches the conflict point within 3.5 s of the ego (ego arrival within 12 s)Collision, <1.8<1.8 m
LTAStops if an opposing track arrives before the ego’s arrival plus a 4.0 s gap (12 s horizon)Collision, <1.8<1.8 m
Appendix
Table 6: Decision rules and violation criteria of the six safety applications.
OperatorChange
Fault vector
Fault magnitudeScales a delay or skew by ×0.5\times 0.5 or ×2\times 2 ; changes a drop count by −5-5 to +10+10 ; scales σ\sigma or shifts bb
Fault windowShifts the offset by ±2.5\pm 2.5 s, resets the duration, or changes the anchor event
Stuck feed ∗SPaT phase and countdown freeze opening 2.5 or 5 s before the amber onset
Outage ∗Window-long drop of the consumed stream (5, 8, or 12 s)
Track freeze ∗Freezes neighbors’ BSM kinematics from 3–8 s before the ego’s decision point
Appendix
Table 7: Mutation operators of specification-space search. ∗ Replaces the scenario’s fault vector.
Figure 8: Condensed system prompts of the three LLM roles of LAST-V2X .
ExperimentScaleSeeds
Normal-traffic benchmark100 prompts, 8 towns1 per scene
Communication-fault suite12 prompts1 per scene
Corridor traversal6 prompts, Town05; 3 offset plans ×\times 3 radio ranges10 (420 runs)
Multiple connected vehicles6 prompts, Town0510 per condition
Refinement suite ‡50 prompts; ≤\leq 120 search candidates and ≤\leq 5 reflection rounds per scene1 per scene
Appendix
Table 8: Experiment configurations. All runs use GPT-4o (temperature 0.2, fixed sampling seed) and synchronous live CARLA simulation, except ‡ search runs, which use the stub backend; the headline mechanisms were validated in live CARLA.
More in this topic

Scenario-Based Testing

See all 12 papers

Explore similar work

CardsList
Sep 23, 2026

Teach-to-Crash: A Closed-Loop Student-Teacher LLM Framework for Collision-Inducing Test Scenario Generation

Validating Autonomous Driving Systems (ADS) in simulation requires testing architectures that can discover rare, safety-critical failures while generating scenarios that are executable, diverse, and useful for downstream failure analysis. We introduce Teach-to-Crash, a closed-loop testing framework that combines a constrained ego-centric scenario representation, stagnation-aware search control, and a dual-LLM architecture for adaptive failure discovery. A high-reasoning Teacher LLM acts as an adaptive search controller, while a low-reasoning Student LLM emits simulator-executable scenarios in a strict JSON schema. The Teacher intervenes only when rolling collision rate and time-to-collision metrics stagnate, providing strategic guidance to redirect the search. In a CARLA case study with two experimental setups that vary the ego vehicle's speed policy, Teach-to-Crash achieves the highest Collision Hit Rate (90.79%), the shortest mean Time-to-Collision (18.31 s), and a competitive Collision Discovery Rate (136.21). PAFOT attains a higher mean CDR (179.44), but with substantially larger variance. Teach-to-Crash also yields the highest diversity (0.547) and, averaged across both setups on the CARLA Traffic Manager controller, the highest avoidability-based usefulness proxy (60.04%) among the compared methods. These results, within the evaluated CARLA scope, provide evidence that closed-loop dual-LLM reasoning can steer adversarial simulation-based testing over a constrained executable program space, generating failures that are frequent, structurally diverse, and assessed as more frequently avoidable.

Zaid Ghazal, Khouloud Gaaloul, Bruce Maxim

University of Michigan-Dearborn Dearborn, MI, USA

Autonomous Driving Safety EvaluationAdversarial Scenario GenerationAutonomous Driving SimulationAutonomous Driving Scenario Generation
AskPDF
Aug 4, 2026

An Inline Control Architecture for Language Models in Intelligent Transportation Systems

Vehicle-to-everything (V2X) systems increasingly incorporate large language models (LLMs) for semantic tasks such as message summarization, operator assistance, and decision support at roadside units and edge nodes. Although these components are not part of safety-critical control loops, they introduce prompt-level attack surfaces that are not addressed by traditional V2X security mechanisms focused on authentication and message integrity. This paper presents Guarded-V2X, an inline semantic guardrail architecture for securing LLM-enabled V2X services under real-time constraints. The proposed system integrates rule-based ingress filtering, a lightweight safety classifier, policy-constrained structured generation, trusted-only retrieval, and post-decision adjudication to enforce machine-checkable safety boundaries prior to downstream execution. Guarded-V2X is evaluated using a four-stage experimental pipeline encompassing intrusion vulnerability analysis, calibration and latency benchmarking, guardrail validation, and robustness under adversarial stress. Experiments are conducted on a V2X-aligned simulated dataset derived from RSU advisories, operator messages, and annotated V2X message summaries. Results show that unguarded and prompt-only baselines retain residual vulnerability under multi-turn adversarial trials, while Guarded-V2X consistently reduces intrusion acceptance success rates and eliminates observed unsafe completions in two-turn settings, without exceeding latency budgets for V2X semantic advisory paths.

Narendra Kumar Dewangan, Mounira Msahli

LTCI, Département Informatique et Réseaux, Télécom Paris, Institut Polytechnique de Paris, France

LLM GuardrailsAdversarial Attacks on LLMsLLM SecurityV2X Communication
AskPDF
May 7, 2026

Traffic Scenario Orchestration from Language via Constraint Satisfaction

Autonomous vehicles (AVs) require extensive testing in simulation, but test case generation for driving scenarios is laborious. The desired scenarios are often out-of-distribution and have precise requirements on interactions with the AV policy under test. Manually programming scenarios allows for precise controllability but is difficult to scale. On the other hand, statistical models can leverage compute and data, but struggle with precise controllability when out-of-distribution. We cast scenario orchestration as a constraint-solving problem and present a language-in, simulation-out scenario orchestrator for closed-loop testing AVs. Our approach leverages foundation model reasoning to translate general, natural language descriptions into a set of constraints as a scenario representation. This then allows us to leverage off the shelf solvers to solve for actor behaviors which meet precise testing intentions in closed-loop. Under a benchmark of carefully crafted and diverse scenario descriptions, our approach greatly outperforms our baselines in orchestration success rate. We further show that our closed-loop approach is especially important for scenarios which require ego-reactive specifications.

Frieda Rong, Chris Zhang, Kelvin Wong +1

University of Toronto · 2Waabi

Autonomous Driving SimulationAutomated Test GenerationAutonomous Driving Scenario Generation
AskPDF