CRASH: Cognitive Reasoning Agent for Safety Hazards in Autonomous Driving

• URL: http://arxiv.org/abs/2603.15364v1
• Date: Mon, 16 Mar 2026 14:39:33 GMT
• Title: CRASH: Cognitive Reasoning Agent for Safety Hazards in Autonomous Driving
• Abstract summary: This work examines real-world AV incidents reported in the NHTSA database.<n>We introduce CRASH, an agent that automates reasoning over crash reports by leveraging both standardized fields and unstructured narrative descriptions.<n>Our findings show that CRASH attributes 64% of incidents to perception or planning failures, underscoring the importance of reasoning-based analysis for accurate fault attribution.<n>We further validate CRASH with five domain experts, achieving 86% accuracy in attributing AV system failures.
• Score: 0.3823356975862005
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: As AVs grow in complexity and diversity, identifying the root causes of operational failures has become increasingly complex. The heterogeneity of system architectures across manufacturers, ranging from end-to-end to modular designs, together with variations in algorithms and integration strategies, limits the standardization of incident investigations and hinders systematic safety analysis. This work examines real-world AV incidents reported in the NHTSA database. We curate a dataset of 2,168 cases reported between 2021 and 2025, representing more than 80 million miles driven. To process this data, we introduce CRASH, Cognitive Reasoning Agent for Safety Hazards, an LLM-based agent that automates reasoning over crash reports by leveraging both standardized fields and unstructured narrative descriptions. CRASH operates on a unified representation of each incident to generate concise summaries, attribute a primary cause, and assess whether the AV materially contributed to the event. Our findings show that (1) CRASH attributes 64% of incidents to perception or planning failures, underscoring the importance of reasoning-based analysis for accurate fault attribution; and (2) approximately 50% of reported incidents involve rear-end collisions, highlighting a persistent and unresolved challenge in autonomous driving deployment. We further validate CRASH with five domain experts, achieving 86% accuracy in attributing AV system failures. Overall, CRASH demonstrates strong potential as a scalable and interpretable tool for automated crash analysis, providing actionable insights to support safety research and the continued development of autonomous driving systems.

Related papers

• When Seeing Overrides Knowing: Visual Dominance and Deferral-Based Method for Personalized Safety in VLMs [54.95635713318535]
  Vision-language models (VLMs) are increasingly deployed in high-stakes settings, where a response that is reasonable in general may still be unsafe for a particular user.<n>We study this problem of personalized safety in multimodal systems and introduce MPS-Bench, a benchmark of 5,181 scenarios from 584 real-world images.<n>We find that they almost always respond directly (86-99%) rather than seek missing context, and none exceeds 2.6/5 on personalized safety.<n>Motivated by this mechanism, we propose PRISM, a lightweight input monitor that uses bidirectional cross-modal modulation to predict when a query is likely to require
  arXiv  Detail & Related papers  (2026-09-03T03:58:56Z)
• Dynamic analysis enhances issue resolution [53.50448142467294]
  DAIRA (Dynamic Analysis-enhanced Issue Resolution Agent) is an automated repair framework that embeds dynamic analysis into the agent's reasoning cycle.<n> Driven by a Test Tracing-Driven methodology, DAIRA utilizes lightweight monitors to extract critical runtime data.<n>When powered by Gemini 3 Flash Preview, DAIRA establishes a new state-of-the-art (SOTA) performance, achieving a 79.4% resolution rate on the SWE-bench Verified dataset.
  arXiv  Detail & Related papers  (2026-03-23T14:48:54Z)
• Automated Self-Testing as a Quality Gate: Evidence-Driven Release Management for LLM Applications [51.56484100374058]
  We present an automated self-testing framework that introduces quality gates with evidence-based release decisions.<n>We evaluate the framework through a longitudinal case study of an internally deployed multi-agent conversational AI system.
  arXiv  Detail & Related papers  (2026-03-13T20:44:15Z)
• AD-R1: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving with Impartial World Models [75.214287449744]
  We introduce a framework for post-training policy refinement built around an Impartial World Model.<n>Our primary contribution is to teach this model to be honest about danger.<n>We demonstrate through extensive experiments, that our model significantly outperforms baselines in predicting failures.
  arXiv  Detail & Related papers  (2025-11-25T13:57:24Z)
• Enhancing reliability in AI inference services: An empirical study on real production incidents [6.549475714716768]
  We present one of the first provider-internal, practice-based analysis of large language model (LLM) inference incidents.<n>We developed a taxonomy and methodology grounded in a year of operational experience, validating it on 156 high-severity incidents.<n>This study demonstrates how systematic, empirically grounded analysis of inference operations can drive more reliable and cost-efficient LLM serving at scale.
  arXiv  Detail & Related papers  (2025-10-17T23:16:29Z)
• From Narratives to Probabilistic Reasoning: Predicting and Interpreting Drivers' Hazardous Actions in Crashes Using Large Language Model [3.3457493284891338]
  Two-vehicle crashes account for approximately 70% of roadway crashes.<n>Driver Hazardous Action (DHA) data is limited by inconsistent and labor-intensive manual coding practices.<n>Here, we present an innovative framework that leverages a fine-tuned large language model to automatically infer DHAs from textual crash narratives.
  arXiv  Detail & Related papers  (2025-10-14T21:35:47Z)
• SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator [77.86600052899156]
  Large Language Model (LLM)-based agents are increasingly deployed in real-world applications.<n>We propose AutoSafe, the first framework that systematically enhances agent safety through fully automated synthetic data generation.<n>We show that AutoSafe boosts safety scores by 45% on average and achieves a 28.91% improvement on real-world tasks.
  arXiv  Detail & Related papers  (2025-05-23T10:56:06Z)
• UniSTPA: A Safety Analysis Framework for End-to-End Autonomous Driving [10.063740202765343]
  We propose the Unified System Theoretic Process Analysis (UniSTPA) framework.<n>UniSTPA performs hazard analysis not only at the component level but also within the model's internal layers.<n>The proposed framework thus offers both theoretical and practical guidance for the safe development and deployment of end-to-end autonomous driving systems.
  arXiv  Detail & Related papers  (2025-05-21T01:23:31Z)
• AILuminate: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons [62.374792825813394]
  This paper introduces AILuminate v1.0, the first comprehensive industry-standard benchmark for assessing AI-product risk and reliability.<n>The benchmark evaluates an AI system's resistance to prompts designed to elicit dangerous, illegal, or undesirable behavior in 12 hazard categories.
  arXiv  Detail & Related papers  (2025-02-19T05:58:52Z)
• Learning Traffic Crashes as Language: Datasets, Benchmarks, and What-if Causal Analyses [76.59021017301127]
  We propose a large-scale traffic crash language dataset, named CrashEvent, summarizing 19,340 real-world crash reports. We further formulate the crash event feature learning as a novel text reasoning problem and further fine-tune various large language models (LLMs) to predict detailed accident outcomes. Our experiments results show that our LLM-based approach not only predicts the severity of accidents but also classifies different types of accidents and predicts injury outcomes.
  arXiv  Detail & Related papers  (2024-06-16T03:10:16Z)
• Towards Automated Driving Violation Cause Analysis in Scenario-Based Testing for Autonomous Driving Systems [22.872694649245044]
  We propose a novel driving violation cause analysis (DVCA) tool. Our tool can achieve perfect component-level attribution accuracy (100%) and almost (>98%) perfect message-level accuracy.
  arXiv  Detail & Related papers  (2024-01-19T01:12:37Z)
• ACAV: A Framework for Automatic Causality Analysis in Autonomous Vehicle Accident Recordings [5.578446693797519]
  Recent fatalities have emphasized the importance of safety validation through large-scale testing. We propose ACAV, an automated framework designed to conduct causality analysis for AV accident recordings. We evaluate ACAV on the Apollo ADS, finding that it can identify five distinct types of causal events in 93.64% of 110 accident recordings.
  arXiv  Detail & Related papers  (2024-01-13T12:41:05Z)

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.