# PersonaDrive: Human-Style Retrieval-Augmented VLA Agents for Closed-Loop Driving Simulation

arXiv: https://arxiv.org/abs/2606.12616 · HTML: https://mlsanity.com/paper/2606.12616/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Imitation-learning end-to-end planners, one of 9 directions in End-to-end autonomous driving.
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Placed in

- End-to-end autonomous driving / [Imitation-learning end-to-end planners](https://mlsanity.com/driving/imitation-learning-end-to-end-planners/)
- 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)

- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [DriveLM: Driving with Graph Visual Question Answering](https://mlsanity.com/paper/2312.14150/) (2023)
- [AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning](https://mlsanity.com/paper/2506.13757/) (2025)
- [Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving](https://mlsanity.com/paper/2406.03877/) (2024)
- [Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline](https://mlsanity.com/paper/2206.08129/) (2022)
- [Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenes](https://mlsanity.com/paper/2305.10430/) (2023)
- [Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving](https://mlsanity.com/paper/2305.06242/) (2023)
- [SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignment](https://mlsanity.com/paper/2503.09594/) (2025)
- [Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail](https://mlsanity.com/paper/2511.00088/) (2025)
- [DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving](https://mlsanity.com/paper/2308.00398/) (2023)
- [RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Model](https://mlsanity.com/paper/2402.10828/) (2024)
- [BehaviorGPT: Smart Agent Simulation for Autonomous Driving with Next-Patch Prediction](https://mlsanity.com/paper/2405.17372/) (2024)
- [HiP-AD: Hierarchical and Multi-Granularity Planning with Deformable Attention for Autonomous Driving in a Single Decoder](https://mlsanity.com/paper/2503.08612/) (2025)
- [MAVERIC: A Data-Driven Approach to Personalized Autonomous Driving](https://mlsanity.com/paper/2301.08595/) (2023)
- [StyleDrive: Towards Driving-Style Aware Benchmarking of End-To-End Autonomous Driving](https://mlsanity.com/paper/2506.23982/) (2025)
- [B-GAP: Behavior-Rich Simulation and Navigation for Autonomous Driving](https://mlsanity.com/paper/2011.03748/) (2020)
- [Driving Style Alignment for LLM-powered Driver Agent](https://mlsanity.com/paper/2403.11368/) (2024)
- [Behaviorally Diverse Traffic Simulation via Reinforcement Learning](https://mlsanity.com/paper/2011.05741/) (2020)
- [Drive My Way: Preference Alignment of Vision-Language-Action Model for Personalized Driving](https://mlsanity.com/paper/2603.25740/) (2026)
- [RealDrive: Retrieval-Augmented Driving with Diffusion Models](https://mlsanity.com/paper/2505.24808/) (2025)

## Abstract (arXiv)

Closed-loop driving simulators typically populate their environments with non-ego traffic agents that behave largely the same way, produced either by rule-based traffic managers or by learned models trained toward a single behavioral mode. Recent work introduces style variation through post-hoc labels on observational data or LLM-inferred reward weights, but these signals act as proxies for what a style should reward rather than demonstrations of humans explicitly asked to drive in that style. We introduce PersonaDrive, a pipeline that conditions a vision-language-action (VLA) driving agent on retrieved demonstrations from a style-instructed human driving dataset, in which participants drive CARLA leaderboard routes under aggressive, neutral, and conservative instructions on a driver-in-the-loop rig. The pipeline has three stages: (i) offline triplet mining over per-style human driving data using a combined image-text similarity score; (ii) training a lightweight retrieval head that fuses frozen visual features with a small control encoder over per-style databases; and (iii) fine-tuning a single VLA backbone to treat retrieved context points as in-context behavioral demonstrations during waypoint prediction. At inference, the same backbone is conditioned on any style by swapping which per-style database the retrieval head queries, so selecting a style requires no per-style retraining while enabling human-style, style-diverse non-ego agents for closed-loop simulation. On Bench2Drive, PersonaDrive (no style) improves the driving score by 4.6% over SimLingo and 2.5% over HiP-AD, and under style conditioning attains the highest driving score in every style within a roughly 2% band (its weakest style surpassing the strongest baseline, DMW, by 5.4%), while average speed and acceleration rise by 18% and 25% from the conservative to the aggressive instruction.