# InSpire: Vision-Language-Action Models with Intrinsic Spatial Reasoning

arXiv: https://arxiv.org/abs/2505.13888 · HTML: https://mlsanity.com/paper/2505.13888/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 16 of its 45 references that are in the map.
- First posted on arXiv 20 May 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)
- Vision-language-action models / [Reasoning and chain-of-thought in VLA](https://mlsanity.com/vla/reasoning-and-chain-of-thought-in-vla/)

## Builds on (most cited first, 16 of 16)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://mlsanity.com/paper/2501.09747/) (2025)
- [Robotic Control via Embodied Chain-of-Thought Reasoning](https://mlsanity.com/paper/2407.08693/) (2024)
- [Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models](https://mlsanity.com/paper/2502.19417/) (2025)
- [RT-H: Action Hierarchies Using Language](https://mlsanity.com/paper/2403.01823/) (2024)
- [Scene Graph Reasoning for Visual Question Answering](https://mlsanity.com/paper/2007.01072/) (2020)
- [Learning Manipulation Skills through Robot Chain-of-Thought with Sparse Failure Guidance](https://mlsanity.com/paper/2405.13573/) (2024)
- [Performance Portable Monte Carlo Particle Transport on Intel, NVIDIA, and AMD GPUs](https://mlsanity.com/paper/2403.12345/) (2024)

## Built on by (most cited first, 21 of 21)

- [Pure Vision Language Action (VLA) Models: A Comprehensive Survey](https://mlsanity.com/paper/2509.19012/) (2025)
- [Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation](https://mlsanity.com/paper/2508.06426/) (2025)
- [Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends](https://mlsanity.com/paper/2506.20966/) (2025)
- [TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking](https://mlsanity.com/paper/2510.07134/) (2025)
- [Reasoning through Exploration: A Reinforcement Learning Framework for Robust Function Calling](https://mlsanity.com/paper/2508.05118/) (2025)
- [Survey of Vision-Language-Action Models for Embodied Manipulation](https://mlsanity.com/paper/2508.15201/) (2025)
- [MAPS: Preserving Vision-Language Representations via Module-Wise Proximity Scheduling for Better Vision-Language-Action Generalization](https://mlsanity.com/paper/2511.19878/) (2025)
- [Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment](https://mlsanity.com/paper/2607.13429/) (2026)
- [FunReason: Enhancing Large Language Models' Function Calling via Self-Refinement Multiscale Loss and Automated Data Refinement](https://mlsanity.com/paper/2505.20192/) (2025)
- [An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges](https://mlsanity.com/paper/2512.11362/) (2025)
- [BFA++: Hierarchical Best-Feature-Aware Token Prune for Multi-View Vision Language Action Model](https://mlsanity.com/paper/2602.20566/) (2026)
- [Embodied Interpretability: Linking Causal Understanding to Generalization in Vision-Language-Action Models](https://mlsanity.com/paper/2605.00321/) (2026)
- [CulinaryCut-VLAP: A Vision-Language-Action-Physics Framework for Food Cutting via a Force-Aware Material Point Method](https://mlsanity.com/paper/2601.06451/) (2026)
- [WorldAgen: Unified State-Action Prediction with Test-Time World Model Training](https://mlsanity.com/paper/2609.08162/) (2026)
- [Beyond the Majority: Long-tail Imitation Learning for Robotic Manipulation](https://mlsanity.com/paper/2602.06512/) (2026)
- [VistaVLA: Geometry- and Semantic-Aware 3D Gaussian-Grounded VLA for Robotic Manipulation](https://mlsanity.com/paper/2607.12356/) (2026)
- [CoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action Model](https://mlsanity.com/paper/2607.25487/) (2026)
- [Human-Centric Image Captioning with Subject-Centered Spatial Understanding](https://mlsanity.com/paper/2609.08300/) (2026)
- [Disentangling Spurious Correlations in Vision-Language-Action Models via Predicting Domain-Invariant Latent Lookahead](https://mlsanity.com/paper/2609.37165/) (2026)
- [SpatialChain: A Benchmark for Auditing Spatial Reasoning Faithfulness in VLMs](https://mlsanity.com/paper/2610.06413/) (2026)
- [RAIN: Robotic Task Generalization with Region-Aware Interaction Networks](https://mlsanity.com/paper/2610.14039/) (2026)

## Abstract (arXiv)

Leveraging pretrained Vision-Language Models (VLMs) to map language instruction and visual observations to raw low-level actions, Vision-Language-Action models (VLAs) hold great promise for achieving general-purpose robotic systems. Despite their advancements, existing VLAs tend to spuriously correlate task-irrelevant visual features with actions, limiting their generalization capacity beyond the training data. To tackle this challenge, we propose Intrinsic Spatial Reasoning (InSpire), a simple yet effective approach that mitigates the adverse effects of spurious correlations by boosting the spatial reasoning ability of VLAs. Specifically, InSpire redirects the VLA's attention to task-relevant factors by prepending the question "In which direction is the [object] relative to the robot?" to the language instruction and aligning the answer "right/left/up/down/front/back/grasped" and predicted actions with ground-truth. Notably, InSpire can be used as a plugin to enhance existing autoregressive VLAs, requiring no extra training data or interaction with other large models. Extensive experimental results in both simulation and real-world environments demonstrate the effectiveness and flexibility of our approach.