# Why Braking? Scenario Extraction and Reasoning Utilizing LLM

arXiv: https://arxiv.org/abs/2507.15874 · HTML: https://mlsanity.com/paper/2507.15874/

## Key facts

- Cited by 1 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 16 of its 21 references that are in the map.
- First posted on arXiv 17 Jul 2025.

## Placed in

- LLM reasoning / [Chain-of-thought reasoning for driving](https://mlsanity.com/lr/chain-of-thought-reasoning-for-driving/)

## Builds on (most cited first, 16 of 16)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [DriveLM: Driving with Graph Visual Question Answering](https://mlsanity.com/paper/2312.14150/) (2023)
- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024)
- [Nomic Embed: Training a Reproducible Long Context Text Embedder](https://mlsanity.com/paper/2402.01613/) (2024)
- [Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior](https://mlsanity.com/paper/2112.05077/) (2021)
- [6-Layer Model for a Structured Description and Categorization of Urban Traffic and Environment](https://mlsanity.com/paper/2012.06319/) (2020)
- [Chat2Scenario: Scenario Extraction From Dataset Through Utilization of Large Language Model](https://mlsanity.com/paper/2404.16147/) (2024)
- [RefAV: Towards Planning-Centric Scenario Mining](https://mlsanity.com/paper/2505.20981/) (2025)
- [1001 Ways of Scenario Generation for Testing of Self-driving Cars: A Survey](https://mlsanity.com/paper/2304.10850/) (2023)
- [Real-World Scenario Mining for the Assessment of Automated Vehicles](https://mlsanity.com/paper/2006.00483/) (2020)
- [Scenario Extraction from a Large Real-World Dataset for the Assessment of Automated Vehicles](https://mlsanity.com/paper/2306.07815/) (2023)

## Built on by (most cited first, 1 of 1)

- [Efficient Cross-Country Data Acquisition Strategy for ADAS via Street-View Imagery](https://mlsanity.com/paper/2602.01836/) (2026)

## Abstract (arXiv)

The growing number of ADAS-equipped vehicles has led to a dramatic increase in driving data, yet most of them capture routine driving behavior. Identifying and understanding safety-critical corner cases within this vast dataset remains a significant challenge. Braking events are particularly indicative of potentially hazardous situations, motivating the central question of our research: Why does a vehicle brake? Existing approaches primarily rely on rule-based heuristics to retrieve target scenarios using predefined condition filters. While effective in simple environments such as highways, these methods lack generalization in complex urban settings. In this paper, we propose a novel framework that leverages Large Language Model (LLM) for scenario understanding and reasoning. Our method bridges the gap between low-level numerical signals and natural language descriptions, enabling LLM to interpret and classify driving scenarios. We propose a dual-path scenario retrieval that supports both category-based search for known scenarios and embedding-based retrieval for unknown Out-of-Distribution (OOD) scenarios. To facilitate evaluation, we curate scenario annotations on the Argoverse 2 Sensor Dataset. Experimental results show that our method outperforms rule-based baselines and generalizes well to OOD scenarios.