# AED: Automatic Discovery of Effective and Diverse Vulnerabilities for Autonomous Driving Policy with Large Language Models

arXiv: https://arxiv.org/abs/2503.20804 · HTML: https://mlsanity.com/paper/2503.20804/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 35 of its 70 references that are in the map.
- First posted on arXiv 24 Mar 2025.

## Placed in

- End-to-end autonomous driving / [Reinforcement learning for driving](https://mlsanity.com/driving/reinforcement-learning-for-driving/)

## Builds on (most cited first, 30 of 35)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [Dueling Network Architectures for Deep Reinforcement Learning](https://mlsanity.com/paper/1511.06581/) (2015)
- [Diversity is All You Need: Learning Skills without a Reward Function](https://mlsanity.com/paper/1802.06070/) (2018)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [Language to Rewards for Robotic Skill Synthesis](https://mlsanity.com/paper/2306.08647/) (2023)
- [PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training](https://mlsanity.com/paper/2106.05091/) (2021)
- [Reward Design with Language Models](https://mlsanity.com/paper/2303.00001/) (2023)
- [Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning](https://mlsanity.com/paper/2302.02662/) (2023)
- [Guiding Pretraining in Reinforcement Learning with Large Language Models](https://mlsanity.com/paper/2302.06692/) (2023)
- [RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback](https://mlsanity.com/paper/2402.03681/) (2024)
- [On a Formal Model of Safe and Scalable Self-driving Cars](https://mlsanity.com/paper/1708.06374/) (2017)
- [Motif: Intrinsic Motivation from Artificial Intelligence Feedback](https://mlsanity.com/paper/2310.00166/) (2023)
- [Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft](https://mlsanity.com/paper/2312.09238/) (2023)
- [Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals](https://mlsanity.com/paper/2302.04449/) (2023)
- [Adversarial Evaluation of Autonomous Vehicles in Lane-Change Scenarios](https://mlsanity.com/paper/2004.06531/) (2020)
- [Learning Multimodal Rewards from Rankings](https://mlsanity.com/paper/2109.12750/) (2021)
- [Failure-Scenario Maker for Rule-Based Agent using Multi-agent Adversarial Reinforcement Learning and its Application to Autonomous Driving](https://mlsanity.com/paper/1903.10654/) (2019)
- [Adaptive Stress Testing with Reward Augmentation for Autonomous Vehicle Validation](https://mlsanity.com/paper/1908.01046/) (2019)
- [Corner Case Generation and Analysis for Safety Assessment of Autonomous Vehicles](https://mlsanity.com/paper/2102.03483/) (2021)
- [Training Adversarial Agents to Exploit Weaknesses in Deep Control Policies](https://mlsanity.com/paper/2002.12078/) (2020)
- [Accelerating Reinforcement Learning of Robotic Manipulations via Feedback from Large Language Models](https://mlsanity.com/paper/2311.02379/) (2023)
- [Too Afraid to Drive: Systematic Discovery of Semantic DoS Vulnerability in Autonomous Driving Planning under Physical-World Attacks](https://mlsanity.com/paper/2201.04610/) (2022)
- [Efficient statistical validation with edge cases to evaluate Highly Automated Vehicles](https://mlsanity.com/paper/2003.01886/) (2020)

## Built on by (most cited first, 2 of 2)

- [Steerable Adversarial Scenario Generation through Test-Time Preference Alignment](https://mlsanity.com/paper/2509.20102/) (2025)
- [From Attacks to Curricula: Learnability-Guided Adversarial Training for Safe Autonomous Driving](https://mlsanity.com/paper/2606.14032/) (2026)

## Abstract (arXiv)

Assessing the safety of autonomous driving policy is of great importance, and reinforcement learning (RL) has emerged as a powerful method for discovering critical vulnerabilities in driving policies. However, existing RL-based approaches often struggle to identify vulnerabilities that are both effective-meaning the autonomous vehicle is genuinely responsible for the accidents-and diverse-meaning they span various failure types. To address these challenges, we propose AED, a framework that uses large language models (LLMs) to automatically discover effective and diverse vulnerabilities in autonomous driving policies. We first utilize an LLM to automatically design reward functions for RL training. Then we let the LLM consider a diverse set of accident types and train adversarial policies for different accident types in parallel. Finally, we use preference-based learning to filter ineffective accidents and enhance the effectiveness of each vulnerability. Experiments across multiple simulated traffic scenarios and tested policies show that AED uncovers a broader range of vulnerabilities and achieves higher attack success rates compared with expert-designed rewards, thereby reducing the need for manual reward engineering and improving the diversity and effectiveness of vulnerability discovery. The implementation can be found on: https://github.com/thu-nics/AED .