Technical Report of RoboSpatial Challenge at CVPR 2026: Selective Reasoning Activation and Reference-Frame Disambiguation for Embodied Spatial Reasoning
On the map: LLM reasoning → Spatial and embodied reasoning
Abstract (arXiv)
Vision-language models achieve strong general perception but often struggle with the spatial reasoning required for embodied tasks. We present RoboSpatialBrain, our submission to the RoboSpatial Challenge at the Embodied Reasoning in Action Workshop, CVPR 2026, built on RoboBrain2.5-8B-NV. RoboSpatialBrain combines two training-free, inference-time mechanisms: a forced <think> prefix activation strategy paired with a task-specific post-prompt that elicits deliberate reasoning on context and compatibility tasks, and an explicit reference-frame redirection pipeline that resolves camera-centric and object-centric ambiguity for context tasks. We additionally explore fine-tuning RoboBrain2.5 on compatibility data and present a detailed analysis of its interaction with prompting. RoboSpatialBrain achieved first place in the RoboSpatial Challenge, with an overall success rate of 80.9% on RoboSpatial-Home. Code is available at https://github.com/YuxiangXie2003/RoboSpatialBrain.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 3 of its 10 references that are in the map. First posted on arXiv 30 Jun 2026.
Builds on
3 of 10 references.
Closest ancestors · 2
Same direction, newest first
- 2026RoboBrain 2.5: Depth in Sight, Time in Mind20 Jan
- 2025ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models27 May
Other references · 1
- 2025Qwen3-VL Technical Reportcited by 2,793
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026RoBoSR: Structured Scene Representations for Embodied Robotic Reasoning ↗
- 2024RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics
- 2025Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
- 2025RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics
- 2026ESPIRE: A Diagnostic Benchmark for Embodied Spatial Reasoning of Vision-Language Models
- 2025Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics
- 2026RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks?
- 2025Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning