# SVBRD-LLM: Self-Verifying Behavioral Rule Discovery for Autonomous Vehicle Identification

arXiv: https://arxiv.org/abs/2511.14977 · HTML: https://mlsanity.com/paper/2511.14977/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Large language models for driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 29 of its 59 references that are in the map.
- First posted on arXiv 18 Nov 2025.

## Placed in

- End-to-end autonomous driving / [Large language models for driving](https://mlsanity.com/driving/large-language-models-for-driving/)

## Builds on (most cited first, 29 of 29)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model](https://mlsanity.com/paper/2310.01412/) (2023)
- [MotionLM: Multi-Agent Motion Forecasting as Language Modeling](https://mlsanity.com/paper/2309.16534/) (2023)
- [LLM4Drive: A Survey of Large Language Models for Autonomous Driving](https://mlsanity.com/paper/2311.01043/) (2023)
- [LLMLight: Large Language Models as Traffic Signal Control Agents](https://mlsanity.com/paper/2312.16044/) (2023)
- [Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review](https://mlsanity.com/paper/2402.10086/) (2024)
- [A Practical Survey on Zero-shot Prompt Design for In-context Learning](https://mlsanity.com/paper/2309.13205/) (2023)
- [TrafficGPT: Viewing, Processing and Interacting with Traffic Foundation Models](https://mlsanity.com/paper/2309.06719/) (2023)
- [Two-stage LLM Fine-tuning with Less Specialization and More Generalization](https://mlsanity.com/paper/2211.00635/) (2022)
- [LC-LLM: Explainable Lane-Change Intention and Trajectory Predictions with Large Language Models](https://mlsanity.com/paper/2403.18344/) (2024)
- [How Interpretable are Reasoning Explanations from Prompting Large Language Models?](https://mlsanity.com/paper/2402.11863/) (2024)
- [CoT-Drive: Efficient Motion Forecasting for Autonomous Driving with LLMs and Chain-of-Thought Prompting](https://mlsanity.com/paper/2503.07234/) (2025)
- [Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning](https://mlsanity.com/paper/2410.04691/) (2024)
- [Language-Driven Interactive Traffic Trajectory Generation](https://mlsanity.com/paper/2405.15388/) (2024)
- [RAD: Retrieval-Augmented Decision-Making of Meta-Actions with Vision-Language Models in Autonomous Driving](https://mlsanity.com/paper/2503.13861/) (2025)
- [Trajectory Prediction Meets Large Language Models: A Survey](https://mlsanity.com/paper/2506.03408/) (2025)
- [Large Language Models Powered Context-aware Motion Prediction in Autonomous Driving](https://mlsanity.com/paper/2403.11057/) (2024)
- [TrajGPT: Controlled Synthetic Trajectory Generation Using a Multitask Transformer-Based Spatiotemporal Model](https://mlsanity.com/paper/2411.04381/) (2024)
- [Towards Explainable Motion Prediction using Heterogeneous Graph Representations](https://mlsanity.com/paper/2212.03806/) (2022)
- [Characteristics Analysis of Autonomous Vehicle Pre-crash Scenarios](https://mlsanity.com/paper/2502.20789/) (2025)
- [Leveraging Large Language Models (LLMs) for Traffic Management at Urban Intersections: The Case of Mixed Traffic Scenarios](https://mlsanity.com/paper/2408.00948/) (2024)
- [Are you a robot? Detecting Autonomous Vehicles from Behavior Analysis](https://mlsanity.com/paper/2403.09571/) (2024)
- [Interaction Dataset of Autonomous Vehicles with Traffic Lights and Signs](https://mlsanity.com/paper/2501.12536/) (2025)
- [Can the Waymo Open Motion Dataset Support Realistic Behavioral Modeling? A Validation Study with Naturalistic Trajectories](https://mlsanity.com/paper/2509.03515/) (2025)
- [KEPT: Knowledge-Enhanced Prediction of Trajectories from Consecutive Driving Frames with Vision-Language Models](https://mlsanity.com/paper/2509.02966/) (2025)

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

- [LLM-MLFFN: Multi-Level Autonomous Driving Behavior Feature Fusion via Large Language Model](https://mlsanity.com/paper/2603.02528/) (2026)

## Abstract (arXiv)

As autonomous vehicles (AVs) are increasingly deployed on public roads, understanding their real-world behaviors is critical for traffic safety analysis and regulatory oversight. However, many data-driven methods lack interpretability and cannot provide verifiable explanations of AV behavior in mixed traffic. This paper proposes SVBRD-LLM, a self-verifying behavioral rule discovery framework that automatically extracts interpretable behavioral rules from real-world traffic videos through zero-shot large language model (LLM) reasoning. The framework first derives vehicle trajectories using YOLOv26-based detection and ByteTrack-based tracking, then computes kinematic features and contextual information. It then employs GPT-5 zero-shot prompting to perform comparative behavioral analysis between AVs and human-driven vehicles (HDVs) across lane-changing and normal driving behaviors, generating 26 structured rule hypotheses that comprises both numerical thresholds and statistical behavioral patterns. These rules are subsequently evaluated through the AV identification task using an independent validation dataset, and iteratively refined through failure case analysis to filter spurious correlations and improve robustness. The resulting rule library contains 20 high-confidence behavioral rules, each including semantic description, quantitative thresholds or behavioral patterns, applicable context, and validation confidence. Experiments conducted on over 1,500 hours of real-world traffic videos from Waymo's commercial operating area demonstrate that the proposed framework achieves 90.0% accuracy and 93.3% F1-score in AV identification, with 98.0% recall. The discovered rules capture key AV traits in smoothness, conservatism, and lane discipline, informing safety assessment, regulatory compliance, and traffic management in mixed traffic. The dataset is available at: svbrd-llm-roadside-video-av.