mlsanityData to 7 Oct 2026

NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoning

arXiv 2602.21172 ↗First posted 24 Feb 2026cs.AI cs.CVcited by 15

On the map: LLM reasoning → Chain-of-thought reasoning for driving

also in 1 more
Abstract (arXiv)

Vision-Language-Action (VLA) models are advancing autonomous driving by replacing modular pipelines with unified end-to-end architectures. However, current VLAs face two expensive requirements: (1) massive dataset collection, and (2) dense reasoning annotations. In this work, we address both challenges with NORD (No Reasoning for Driving). Compared to existing VLAs, NORD achieves competitive performance while being fine-tuned on <60% of the data and no reasoning annotations, resulting in 3x fewer tokens. We identify that standard Group Relative Policy Optimization (GRPO) fails to yield significant improvements when applied to policies trained on such small, reasoning-free datasets. We show that this limitation stems from difficulty bias, which disproportionately penalizes reward signals from scenarios that produce high-variance rollouts within GRPO. NORD overcomes this by incorporating Dr. GRPO, a recent algorithm designed to mitigate difficulty bias in LLMs. As a result, NORD achieves competitive performance on Waymo and NAVSIM with a fraction of the training data and no reasoning overhead, enabling more efficient autonomous systems. Website: https://nord-vla-ai.github.io/

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Placed in Chain-of-thought reasoning for driving, one of 17 directions in LLM reasoning. Builds on 21 of its 51 references that are in the map. First posted on arXiv 24 Feb 2026.

Builds on

21 of 51 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail30 Oct
  2. 2025More Than Meets the Eye? Uncovering the Reasoning-Planning Disconnect in Training Vision-Language Driving Models6 Oct
  3. 2025AdaThinkDrive: Adaptive Thinking via Reinforcement Learning for Autonomous Driving17 Sep
  4. 2025DriveAgent-R1: Advancing VLM-based Autonomous Driving with Active Perception and Hybrid Thinking28 Jul
  5. 2025HMVLM: Multistage Reasoning-Enhanced Vision-Language Model for Long-Tailed Driving Scenarios6 Jun
  6. 2025AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving21 May

Other references · 15

  1. 2025Qwen2.5-VL Technical Reportcited by 5,418
  2. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 1,980
  3. 2025Process Reinforcement through Implicit Rewardscited by 478
  4. 2024Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillationcited by 244
  5. 2025ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Drivingcited by 190
  6. 2025GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoningcited by 147
  7. 2025GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Datacited by 120
  8. 2025EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videoscited by 116
  9. 2025Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoningcited by 89
  10. 2025DiffVLA: Vision-Language Guided Diffusion Planning for Autonomous Drivingcited by 64
  11. 2025Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Modelscited by 60
  12. 2025AutoDrive-R2: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Drivingcited by 32
3 more
  1. 2025Diffusion Trajectory-guided Policy for Long-horizon Robot Manipulationcited by 15
  2. 2025Poutine: Vision-Language-Trajectory Pre-Training and Reinforcement Learning Post-Training Enable Robust End-to-End Autonomous Drivingcited by 11
  3. 2025DARO: Difficulty-Aware Reweighting Policy Optimizationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 15.

15 papers.

Sort:

By area:

  1. 2026UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Drivingcited by 17
  2. 2026SpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Modelcited by 15
  3. 2026Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Drivingcited by 8
  4. 2026SimWAM: A Simple World Action Model for End-to-End Autonomous Drivingcited by 5
  5. 2026DriveMA: Driving Vision-Language-Action Models with verifiable Meta-Actionscited by 2
  6. 2026IDOL: Inverse-Dynamics-Guided Future Prediction for End-to-End Autonomous Drivingcited by 2
  7. 2026Post-Training in End-to-End Autonomous Drivingcited by 2
  8. 2026Driving Intents Amplify Planning-Oriented Reinforcement Learningcited by 1
  9. 2026DriveMA: Rethinking Language Interfaces in Driving VLAs with One-Step Meta-Actionscited by 1
  10. 2026D3-MoE:Dual Disentangled Diffusion Mixture-of-Experts for Style-Controllable End-to-End Autonomous Drivingcited by 0
  11. 2026Latent-Centroid Steering: Single-Pass Classifier-Free Guidance for Command-Aligned Autonomous Drivingcited by 0
  12. 2026SPVC: Structured and Panoptic Video Fixing for Cross-Dataset Driving Scene Renderingcited by 0
3 more
  1. 2026RAF-VLA: Representation Alignment with the Future for End-to-End Autonomous Drivingcited by 0
  2. 2026CAR-VLA: Complexity-Aware and Risk-Adaptive Reasoning for Autonomous Drivingcited by 0
  3. 2026When the Score Becomes the Target: Rethinking Metric Validity in Autonomous Drivingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Reasoning-VLA: A Fast and General Vision-Language-Action Reasoning Model for Autonomous Driving
  2. 2025AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning
  3. 2026Rethinking Language's Role in Efficient VLA for Autonomous Vehicles: Toward Smarter, Trustworthy Driving
  4. 2026Orion-Lite: Distilling LLM Reasoning into Efficient Vision-Only Driving Models
  5. 2026SteerVLA: Steering Vision-Language-Action Models in Long-Tail Driving Scenarios
  6. 2026Judge, Then Drive: A Critic-Centric Vision Language Action Framework for Autonomous Driving
  7. 2025Drive-R1: Bridging Reasoning and Planning in VLMs for Autonomous Driving with Reinforcement Learning
  8. 2025DeeAD: Dynamic Early Exit of Vision-Language Action for Efficient Autonomous Driving