# SpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model

arXiv: https://arxiv.org/abs/2604.19710 · HTML: https://mlsanity.com/paper/2604.19710/

## Key facts

- Cited by 17 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 59 of its 73 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Placed in

- LLM reasoning / [Chain-of-thought reasoning for driving](https://mlsanity.com/lr/chain-of-thought-reasoning-for-driving/)
- Vision-language-action models / [VLA for autonomous driving](https://mlsanity.com/vla/vla-for-autonomous-driving/)
- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 30 of 59)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [VAD: Vectorized Scene Representation for Efficient Autonomous Driving](https://mlsanity.com/paper/2303.12077/) (2023)
- [Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset](https://mlsanity.com/paper/2104.10133/) (2021)
- [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)
- [TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving](https://mlsanity.com/paper/2205.15997/) (2022)
- [NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking](https://mlsanity.com/paper/2406.15349/) (2024)
- [GPT-Driver: Learning to Drive with GPT](https://mlsanity.com/paper/2310.01415/) (2023)
- [DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving](https://mlsanity.com/paper/2411.15139/) (2024)
- [π*0.6: a VLA That Learns From Experience](https://mlsanity.com/paper/2511.14759/) (2025)
- [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)
- [Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation](https://mlsanity.com/paper/2406.06978/) (2024)
- [EMMA: End-to-End Multimodal Model for Autonomous Driving](https://mlsanity.com/paper/2410.23262/) (2024)
- [ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving](https://mlsanity.com/paper/2506.08052/) (2025)
- [OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model](https://mlsanity.com/paper/2503.23463/) (2025)
- [FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving](https://mlsanity.com/paper/2505.17685/) (2025)
- [Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving](https://mlsanity.com/paper/2410.22313/) (2024)
- [End-to-End Driving with Online Trajectory Evaluation via BEV World Model](https://mlsanity.com/paper/2504.01941/) (2025)
- [Pseudo-Simulation for Autonomous Driving](https://mlsanity.com/paper/2506.04218/) (2025)
- [Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail](https://mlsanity.com/paper/2511.00088/) (2025)
- [DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving](https://mlsanity.com/paper/2510.12796/) (2025)
- [VLP: Vision Language Planning for Autonomous Driving](https://mlsanity.com/paper/2401.05577/) (2024)
- [AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning](https://mlsanity.com/paper/2503.07608/) (2025)
- [Towards learning-based planning:The nuPlan benchmark for real-world autonomous driving](https://mlsanity.com/paper/2403.04133/) (2024)

## Built on by (most cited first, 17 of 17)

- [DriveFuture: Future-Aware Latent World Models for Autonomous Driving](https://mlsanity.com/paper/2605.09701/) (2026)
- [nuReasoning: A Reasoning-Centric Dataset and Benchmark for Long-Tail Autonomous Driving](https://mlsanity.com/paper/2605.31572/) (2026)
- [Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving](https://mlsanity.com/paper/2609.00111/) (2026)
- [Test-Time Trajectory Optimization for Autonomous Driving](https://mlsanity.com/paper/2606.07170/) (2026)
- [GraphWorld: Long-Horizon Planning with World Models for End-to-End Autonomous Driving](https://mlsanity.com/paper/2606.16274/) (2026)
- [MDrive: Benchmarking Closed-Loop Cooperative Driving for End-to-End Multi-agent Systems](https://mlsanity.com/paper/2605.10904/) (2026)
- [ChainFlow-VLA: Causal Flow Planning with Vision-Language Models](https://mlsanity.com/paper/2605.23270/) (2026)
- [SafeAlign-VLA: A Negative-Enhanced Safe Alignment Framework for Risk-Aware Autonomous Driving](https://mlsanity.com/paper/2605.19524/) (2026)
- [Post-Training in End-to-End Autonomous Driving](https://mlsanity.com/paper/2607.08072/) (2026)
- [Large Discrete Policy: Advancing Explicit Behavior Modeling with Stochastic Iterative Scoring](https://mlsanity.com/paper/2609.07049/) (2026)
- [BehaviorWorldGen: Closing the Loop between Action Models and World Simulators via Controllable Behavior-Aware Structured World Generation](https://mlsanity.com/paper/2608.22187/) (2026)
- [NavSafe-∞: Benchmarking Closed-Loop Driving Safety in Photorealistic Environments](https://mlsanity.com/paper/2609.26618/) (2026)
- [Evaluation Is All You Need for Multi-Modal Autonomous Driving](https://mlsanity.com/paper/2609.30818/) (2026)
- [MomWorld: Momentum-Aware Latent World Model for Long-Horizon Autonomous Driving](https://mlsanity.com/paper/2609.33737/) (2026)
- [Beyond Retrieval Relevance: Scene-Grounded Risk Entailment for Vision-Language Driving](https://mlsanity.com/paper/2609.34145/) (2026)
- [Grounding What Shapes the Plan: Rethinking Groundedness for Physical Intelligence in Autonomous Driving](https://mlsanity.com/paper/2610.07521/) (2026)
- [VeriFine: Scaling Verification for Self-Improvement in Embodied Reasoning](https://mlsanity.com/paper/2610.08761/) (2026)

## Abstract (arXiv)

Vision-Language-Action (VLA) models bring rich world knowledge and reasoning capabilities to autonomous driving. However, most driving VLAs are trained only on positive expert demonstrations, which teach models what to do but provide limited supervision on which behaviors to avoid and how to recover from these failures, leading to limited robustness. We introduce SpanVLA, a robust and efficient driving VLA, together with nuReasoning-NR, the first real-world driving dataset and benchmark for learning from negative and recovery samples. An extension of nuReasoning, it comprises 36K reasoning-intensive driving scenarios, including 3K suboptimal trajectories and 3K expert recovery trajectories. To exploit their asymmetric supervision, we introduce Negative--Recovery Reinforcement Fine-Tuning (NR-RFT), which penalizes undesirable behaviors and rewards expert corrective actions. Because challenging scenarios produce rollout groups dominated by similar suboptimal or even infeasible trajectories, it further incorporates an advantage correction to preserve informative optimization signals and encourage exploration. For efficient action generation, SpanVLA retains autoregressive reasoning and introduces a lightweight flow-matching action bridge conditioned on sparse-layer KV caches and initialized from the historical trajectory. Extensive experiments on NAVSIM v1/v2, nuReasoning, and the nuReasoning-NR benchmark demonstrate strong and robust planning performance and efficient action generation. Qualitative results across diverse challenging scenarios further highlight its planning robustness and recovery capability. The dataset and benchmark code will be released to support future research.