# NuRisk: A Visual Question Answering Dataset for Agent-Level Risk Assessment in Autonomous Driving

arXiv: https://arxiv.org/abs/2509.25944 · HTML: https://mlsanity.com/paper/2509.25944/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Chain-of-thought reasoning for driving, one of 17 directions in LLM reasoning.
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Placed in

- LLM reasoning / [Chain-of-thought reasoning for driving](https://mlsanity.com/lr/chain-of-thought-reasoning-for-driving/)
- End-to-end autonomous driving / [VLMs for autonomous driving](https://mlsanity.com/driving/vlms-for-autonomous-driving/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 21 of 21)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset](https://mlsanity.com/paper/2104.10133/) (2021)
- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023)
- [Vision Language Models in Autonomous Driving: A Survey and Outlook](https://mlsanity.com/paper/2310.14414/) (2023)
- [Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous Driving](https://mlsanity.com/paper/2312.03661/) (2023)
- [Talk2BEV: Language-enhanced Bird's-eye View Maps for Autonomous Driving](https://mlsanity.com/paper/2310.02251/) (2023)
- [Holistic Autonomous Driving Understanding by Bird's-Eye-View Injected Multi-Modal Large Models](https://mlsanity.com/paper/2401.00988/) (2024)
- [Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis](https://mlsanity.com/paper/2506.11526/) (2025)
- [DriveLMM-o1: A Step-by-Step Reasoning Dataset and Large Multimodal Model for Driving Scenario Understanding](https://mlsanity.com/paper/2503.10621/) (2025)
- [NuPlanQA: A Large-Scale Dataset and Benchmark for Multi-View Driving Scene Understanding in Multi-Modal Large Language Models](https://mlsanity.com/paper/2503.12772/) (2025)
- [TUMTraffic-VideoQA: A Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes](https://mlsanity.com/paper/2502.02449/) (2025)
- [Are Vision LLMs Road-Ready? A Comprehensive Benchmark for Safety-Critical Driving Video Understanding](https://mlsanity.com/paper/2504.14526/) (2025)
- [Is it safe to cross? Interpretable Risk Assessment with GPT-4V for Safety-Aware Street Crossing](https://mlsanity.com/paper/2402.06794/) (2024)
- [From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios](https://mlsanity.com/paper/2502.02145/) (2025)
- [A new Taxonomy for Automated Driving: Structuring Applications based on their Operational Design Domain, Level of Automation and Automation Readiness](https://mlsanity.com/paper/2404.17044/) (2024)
- [INSIGHT: Enhancing Autonomous Driving Safety through Vision-Language Models on Context-Aware Hazard Detection and Edge Case Evaluation](https://mlsanity.com/paper/2502.00262/) (2025)
- [Vision Foundation Model Embedding-Based Semantic Anomaly Detection](https://mlsanity.com/paper/2505.07998/) (2025)
- [LATTE: Lightweight Attention-based Traffic Accident Anticipation Engine](https://mlsanity.com/paper/2504.04103/) (2025)
- [Bridging Human Oversight and Black-box Driver Assistance: Vision-Language Models for Predictive Alerting in Lane Keeping Assist Systems](https://mlsanity.com/paper/2505.11535/) (2025)

## Built on by (most cited first, 6 of 6)

- [V2X-QA: A Comprehensive Reasoning Dataset and Benchmark for Multimodal Large Language Models in Autonomous Driving Across Ego, Infrastructure, and Cooperative Views](https://mlsanity.com/paper/2604.02710/) (2026)
- [A knowledge-augmented dataset of high-risk driving scenarios with LLM annotations for autonomous driving](https://mlsanity.com/paper/2607.07103/) (2026)
- [Chat2Scenic: An Iterative RAG-Based Framework for Scenario Generation in Autonomous Driving](https://mlsanity.com/paper/2607.14387/) (2026)
- [Can VLMs Unlock Semantic Anomaly Detection? A Framework for Structured Reasoning](https://mlsanity.com/paper/2510.18034/) (2025)
- [Drive by Hindsight and Foresight: Tool-Grounded Synergistic Reasoning over Hierarchical Memory for Autonomous Driving](https://mlsanity.com/paper/2609.08217/) (2026)
- [LLM-Guided Transformation of Non-Critical Driving Scenes into Safety-Critical Scenarios Using Augmented Reality](https://mlsanity.com/paper/2609.20318/) (2026)

## Abstract (arXiv)

Understanding risk in autonomous driving requires not only perception and prediction, but also high-level reasoning about agent behavior and context. Current Vision Language Model (VLM)-based methods primarily ground agents in static images and provide qualitative judgments, lacking the spatio-temporal reasoning needed to capture how risks evolve over time. To address this gap, we propose NuRisk, a comprehensive Visual Question Answering (VQA) dataset comprising 2.9K scenarios and 1.1M agent-level samples, built on real-world data from nuScenes and Waymo, completed with safety-critical scenarios from the CommonRoad simulator. The dataset provides Bird's-eye view (BEV) based sequential images with quantitative, agent-level risk annotations, enabling spatio-temporal reasoning. We benchmark well-known VLMs across different prompting techniques and find that they fail to perform explicit spatio-temporal reasoning, resulting in a peak accuracy of 33% at high latency. To address these shortcomings, our fine-tuned 7B VLM agent improves accuracy to 41% and reduces latency by 75%, demonstrating explicit spatio-temporal reasoning capabilities that proprietary models lacked. While this represents a significant step forward, the modest accuracy underscores the profound challenge of the task, establishing NuRisk as a critical benchmark for advancing spatio-temporal reasoning in autonomous driving. More information can be found at https://github.com/TUM-AVS/NuRisk.