# SVQA-R1: Reinforcing Spatial Reasoning in MLLMs via View-Consistent Reward Optimization

arXiv: https://arxiv.org/abs/2506.01371 · HTML: https://mlsanity.com/paper/2506.01371/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 15 of its 39 references that are in the map.
- First posted on arXiv 2 Jun 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/)

## Builds on (most cited first, 15 of 15)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2504.06958/) (2025)
- [SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models](https://mlsanity.com/paper/2504.11468/) (2025)
- [Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models](https://mlsanity.com/paper/2503.20752/) (2025)
- [MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs](https://mlsanity.com/paper/2503.13111/) (2025)
- [TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning](https://mlsanity.com/paper/2504.09641/) (2025)
- [Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models](https://mlsanity.com/paper/2409.09788/) (2024)
- [Super-resolution image display using diffractive decoders](https://mlsanity.com/paper/2206.07281/) (2022)
- [A Comprehensive Survey on Deep Learning Techniques in Educational Data Mining](https://mlsanity.com/paper/2309.04761/) (2023)

## Built on by (most cited first, 16 of 16)

- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective](https://mlsanity.com/paper/2509.18905/) (2025)
- [Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings](https://mlsanity.com/paper/2602.13823/) (2026)
- [SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL](https://mlsanity.com/paper/2512.04069/) (2025)
- [SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards](https://mlsanity.com/paper/2511.07403/) (2025)
- [SpinBench: Perspective and Rotation as a Lens on Spatial Reasoning in VLMs](https://mlsanity.com/paper/2509.25390/) (2025)
- [Reinforcement Learning for Large Model: A Survey](https://mlsanity.com/paper/2508.08189/) (2025)
- [COOPER: A Unified Model for Cooperative Perception and Reasoning in Spatial Intelligence](https://mlsanity.com/paper/2512.04563/) (2025)
- [Video2Layout: Recall and Reconstruct Metric-Grounded Cognitive Map for Spatial Reasoning](https://mlsanity.com/paper/2511.16160/) (2025)
- [RAU: Reference-based Anatomical Understanding with Vision Language Models](https://mlsanity.com/paper/2509.22404/) (2025)
- [Reasoning Beyond Literal: Cross-style Multimodal Reasoning for Figurative Language Understanding](https://mlsanity.com/paper/2601.17197/) (2026)
- [Unfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning](https://mlsanity.com/paper/2609.03729/) (2026)
- [GaugeVLM: Structuring Spatial Supervision with Measured Geometric Interventions](https://mlsanity.com/paper/2609.38285/) (2026)
- [SpatialCORE: Confidence-Aware Grounded Spatial Reasoning in Large Vision--Language Models](https://mlsanity.com/paper/2609.38716/) (2026)
- [Soft Spatial Reasoning](https://mlsanity.com/paper/2609.38717/) (2026)
- [From Reasoning Failures to Composable Video Spatial Intelligence](https://mlsanity.com/paper/2610.01999/) (2026)

## Abstract (arXiv)

Spatial reasoning remains a critical yet underdeveloped capability in existing vision-language models (VLMs), especially for Spatial Visual Question Answering (Spatial VQA) tasks that require understanding relative positions, distances, and object configurations. Inspired by the R1 paradigm introduced in DeepSeek-R1, which enhances reasoning in language models through rule-based reinforcement learning (RL), we propose SVQA-R1, the first framework to extend R1-style training to spatial VQA. In particular, we introduce Spatial-GRPO, a novel group-wise RL strategy that constructs view-consistent rewards by perturbing spatial relations between objects, e.g., mirror flipping, thereby encouraging the model to develop a consistent and grounded understanding of space. Our model, SVQA-R1, not only achieves dramatically improved accuracy on spatial VQA benchmarks but also exhibits interpretable reasoning paths even without using supervised fine-tuning (SFT) data. Extensive experiments and visualization demonstrate the effectiveness of SVQA-R1 across multiple spatial reasoning benchmarks.