Cover Image

SAFE: Harnessing LLM for Scenario-Driven ADS Testing from Multimodal Crash Data

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Luo, Siwei, Zhang, Yang, Deng, Yao, Liang, Linfeng, Zheng, Xi
Format:	Preprint
Published:	2025
Subjects:	Software Engineering
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AutoMT: A Multi-Agent LLM Framework for Automated Metamorphic Testing of Autonomous Driving Systems
by: Liang, Linfeng, et al.
Published: (2025)

TARGET: Automated Scenario Generation from Traffic Rules for Testing Autonomous Vehicles via Validated LLM-Guided Knowledge Extraction
by: Deng, Yao, et al.
Published: (2023)

From Particles to Perils: SVGD-Based Hazardous Scenario Generation for Autonomous Driving Systems Testing
by: Liang, Linfeng, et al.
Published: (2026)

MARL-OT: Multi-Agent Reinforcement Learning Guided Online Fuzzing to Detect Safety Violation in Autonomous Driving Systems
by: Liang, Linfeng, et al.
Published: (2025)

OpenCat: Improving Interoperability of ADS Testing
by: Ali, Qurban, et al.
Published: (2025)

A Step-by-Step Guide to Creating a Robust Autonomous Drone Testing Pipeline
by: Jiang, Yupeng, et al.
Published: (2025)

HarnessLLM: Automatic Testing Harness Generation via Reinforcement Learning
by: Liu, Yujian, et al.
Published: (2025)

An LLM-driven Scenario Generation Pipeline Using an Extended Scenic DSL for Autonomous Driving Safety Validation
by: Safa, Fida Khandaker, et al.
Published: (2026)

GPTrace: Effective Crash Deduplication Using LLM Embeddings
by: Herter, Patrick, et al.
Published: (2025)

Scenario-Guided LLM-based Mobile App GUI Testing
by: Yu, Shengcheng, et al.
Published: (2025)

Finding the Needle in the Crash Stack: Industrial-Scale Crash Root Cause Localization with AutoCrashFL
by: Kang, Sungmin, et al.
Published: (2025)

Outrunning LLM Cutoffs: A Live Kernel Crash Resolution Benchmark for All
by: Huang, Chenxi, et al.
Published: (2026)

On-Demand Scenario Generation for Testing Automated Driving Systems
by: Yan, Songyang, et al.
Published: (2025)

A Study of Using Multimodal LLMs for Non-Crash Functional Bug Detection in Android Apps
by: Ju, Bangyan, et al.
Published: (2024)

AugmenTest: Enhancing Tests with LLM-Driven Oracles
by: Khandaker, Shaker Mahmud, et al.
Published: (2025)

GARL: Genetic Algorithm-Augmented Reinforcement Learning to Detect Violations in Marker-Based Autonomous Landing Systems
by: Liang, Linfeng, et al.
Published: (2023)

CrashJS: A NodeJS Benchmark for Automated Crash Reproduction
by: Oliver, Philip, et al.
Published: (2024)

ISS-Scenario: Scenario-based Testing in CARLA
by: Li, Renjue, et al.
Published: (2024)

DaiFu: In-Situ Crash Recovery for Deep Learning Systems
by: He, Zilong, et al.
Published: (2025)

Unit Test Update through LLM-Driven Context Collection and Error-Type-Aware Refinement
by: Zhang, Yuanhe, et al.
Published: (2025)

Crash-free Deductive Verifiers
by: Nauta, Wander, et al.
Published: (2026)

DynNPC: Finding More Violations Induced by ADS in Simulation Testing through Dynamic NPC Behavior Generation
by: Lu, You, et al.
Published: (2024)

Generalizing Test Cases for Comprehensive Test Scenario Coverage
by: Qi, Binhang, et al.
Published: (2026)

Improving LLM-Driven Test Generation by Learning from Mocking Information
by: Lee, Jamie, et al.
Published: (2026)

Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
by: Lin, Jiahang, et al.
Published: (2026)

Perception-Guided Fuzzing for Simulated Scenario-Based Testing of Autonomous Driving Systems
by: Pham, Tri Minh Triet, et al.
Published: (2024)

Beyond Crash-to-Patch: Patch Evolution for Linux Kernel Repair
by: Bai, Luyao, et al.
Published: (2026)

Can AI Generate more Comprehensive Test Scenarios? Review on Automated Driving Systems Test Scenario Generation Methods
by: Zhou, Ji, et al.
Published: (2025)

HarnessAgent: Scaling Automatic Fuzzing Harness Construction with Tool-Augmented LLM Pipelines
by: Yang, Kang, et al.
Published: (2025)

LLM-Agents Driven Automated Simulation Testing and Analysis of small Uncrewed Aerial Systems
by: Duvvuru, Venkata Sai Aswath, et al.
Published: (2025)

ChatUniTest: A Framework for LLM-Based Test Generation
by: Chen, Yinghao, et al.
Published: (2023)

Scenario-Based Field Testing of Drone Missions
by: Vierhauser, Michael, et al.
Published: (2024)

Predicting the Impact of Crashes Across Release Channels
by: Mujahid, Suhaib, et al.
Published: (2024)

Code-Survey: An LLM-Driven Methodology for Analyzing Large-Scale Codebases
by: Zheng, Yusheng, et al.
Published: (2024)

SoVAR: Building Generalizable Scenarios from Accident Reports for Autonomous Driving Testing
by: Guo, An, et al.
Published: (2024)

Automated Functional Testing for Malleable Mobile Application Driven from User Intent
by: Wang, Yuying, et al.
Published: (2026)

Practical, Automated Scenario-based Mobile App Testing
by: Yu, Shengcheng, et al.
Published: (2024)

Scenario-based System Testing for Distributed Robotics Applications
by: Peleska, Jan, et al.
Published: (2026)

Text2Scenario: Text-Driven Scenario Generation for Autonomous Driving Test
by: Cai, Xuan, et al.
Published: (2025)

Scaling Test-Driven Code Generation from Functions to Classes: An Empirical Study
by: Liang, Yunhao, et al.
Published: (2026)