mlsanityData to 7 Oct 2026

NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models

arXiv 2603.09542 ↗First posted 10 Mar 2026cs.ROcited by 1

On the map: Vision-language-action models → Generalist VLA models and benchmarks

Abstract (arXiv)

Vision-Language-Action (VLA) models are formulated to ground instructions in visual context and generate action sequences for robotic manipulation. Despite recent progress, VLA models still face structure-blind backbones, backbone-bound generalization, and flat single-objective optimization. To address these challenges, we propose a novel Neuro-Symbolic Vision-Language-Action (NS-VLA) framework. It introduces a Neuro-Symbolic Encoder for plan-constrained primitive inference, a Neuro-Symbolic Solver that conditions a backbone-agnostic policy on the active primitive, and Hierarchical Joint Policy Optimization with reward-granularity matching. Experiments on robotic manipulation benchmarks demonstrate that NS-VLA outperforms previous methods in both one-shot training and data-perturbed settings, while simultaneously exhibiting superior zero-shot generalizability and expanded exploration space. Our code is publicly available.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Generalist VLA models and benchmarks, one of 13 directions in Vision-language-action models. Builds on 72 of its 84 references that are in the map. First posted on arXiv 10 Mar 2026.

Builds on

72 of 84 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model11 Sep
  2. 2025NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks28 Apr
  3. 2025π0.5: a Vision-Language-Action Model with Open-World Generalization22 Apr
  4. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success27 Feb
  5. 2024π0: A Vision-Language-Action Flow Model for General Robot Control31 Oct
  6. 2024A Dual Process VLA: Efficient Robotic Manipulation Leveraging VLM21 Oct
  7. 2024Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation10 Oct
  8. 2024OpenVLA: An Open-Source Vision-Language-Action Model13 Jun
  9. 2024RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation6 Jun
  10. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul

Other references · 62

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  5. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  6. 2015Trust Region Policy Optimizationcited by 2,503
  7. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  8. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  9. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  10. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  11. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  12. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
38 more
  1. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
  2. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,057
  3. 2021A Minimalist Approach to Offline Reinforcement Learningcited by 882
  4. 2021DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsificationcited by 849
  5. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
  6. 2022A Generalist Agentcited by 802
  7. 2023VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Modelscited by 733
  8. 2019Behavior Regularized Offline Reinforcement Learningcited by 654
  9. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 616
  10. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 564
  11. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 517
  12. 2021Implicit Behavioral Cloningcited by 442
  13. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 440
  14. 2016The Option-Critic Architecturecited by 433
  15. 2025UniVLA: Learning to Act Anywhere with Task-centric Latent Actionscited by 386
  16. 2023Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoningcited by 379
  17. 2019The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervisioncited by 369
  18. 2025WorldVLA: Towards Autoregressive Action World Modelcited by 351
  19. 2024Robotic Control via Embodied Chain-of-Thought Reasoningcited by 340
  20. 2017FeUdal Networks for Hierarchical Reinforcement Learningcited by 328
  21. 20243D-VLA: A 3D Vision-Language-Action Generative World Modelcited by 320
  22. 2024TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policiescited by 298
  23. 2016Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivationcited by 282
  24. 2025LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Modelscited by 278
  25. 2020Neurosymbolic AI: The 3rd Wavecited by 253
  26. 2017One-Shot Visual Imitation Learning via Meta-Learningcited by 225
  27. 2016Modular Multitask Reinforcement Learning with Policy Sketchescited by 200
  28. 2025VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learningcited by 166
  29. 2024Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformerscited by 145
  30. 2025SimpleVLA-RL: Scaling VLA Training via Reinforcement Learningcited by 141
  31. 2025Interactive Post-Training for Vision-Language-Action Modelscited by 129
  32. 2021TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?cited by 127
  33. 2018Neural Nearest Neighbors Networkscited by 98
  34. 2024BAKU: An Efficient Transformer for Multi-Task Policy Learningcited by 80
  35. 2025CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsificationcited by 70
  36. 2025HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representationcited by 68
  37. 2019Neural Module Networks for Reasoning over Textcited by 65
  38. 2025VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulatorscited by 65

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Sequential Planning via Anchored Robotic Keypointscited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2025Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey
  2. 2026The Price Is Not Right: Neuro-Symbolic Methods Outperform VLAs on Structured Long-Horizon Manipulation Tasks with Significantly Lower Energy Consumption
  3. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey
  4. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
  5. 2026AC^2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulation
  6. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Review
  7. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation
  8. 2026CoRE-VLA: Towards Scalable and Robust Vision-Language-Action Modeling via Conditional Routing of Experts