# CoV: Chain-of-View Prompting for Spatial Reasoning arXiv: https://arxiv.org/abs/2601.05172 ยท HTML: https://mlsanity.com/paper/2601.05172/ ## Key facts - Cited by 9 papers in the map (data through 14 Oct 2026). - Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. - Builds on 26 of its 47 references that are in the map. - First posted on arXiv 8 Jan 2026. ## Placed in - LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/) ## Builds on (most cited first, 26 of 26) - [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023) - [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025) - [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024) - [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025) - [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024) - [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023) - [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024) - [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025) - [Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI](https://mlsanity.com/paper/2109.08238/) (2021) - [LLaVA-Video: Video Instruction Tuning With Synthetic Data](https://mlsanity.com/paper/2410.02713/) (2024) - [GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://mlsanity.com/paper/2507.01006/) (2025) - [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024) - [An Embodied Generalist Agent in 3D World](https://mlsanity.com/paper/2311.12871/) (2023) - [ScanQA: 3D Question Answering for Spatial Scene Understanding](https://mlsanity.com/paper/2112.10482/) (2021) - [SQA3D: Situated Question Answering in 3D Scenes](https://mlsanity.com/paper/2210.07474/) (2022) - [LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness](https://mlsanity.com/paper/2409.18125/) (2024) - [Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers](https://mlsanity.com/paper/2312.08168/) (2023) - [Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning](https://mlsanity.com/paper/2403.11401/) (2024) - [Towards Learning a Generalist Model for Embodied Navigation](https://mlsanity.com/paper/2312.02010/) (2023) - [Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding](https://mlsanity.com/paper/2412.00493/) (2024) - [GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models](https://mlsanity.com/paper/2501.01428/) (2025) - [ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles](https://mlsanity.com/paper/2405.14062/) (2024) - [Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQA](https://mlsanity.com/paper/2402.15933/) (2024) - [DC-Scene: Data-Centric Learning for 3D Scene Understanding](https://mlsanity.com/paper/2505.15232/) (2025) - [3D CoCa: Contrastive Learners are 3D Captioners](https://mlsanity.com/paper/2504.09518/) (2025) - [Calibrating Where It Matters: Constrained Temperature Scaling](https://mlsanity.com/paper/2406.11456/) (2024) ## Built on by (most cited first, 9 of 9) - [Think3D: Thinking with Space for Spatial Reasoning](https://mlsanity.com/paper/2601.13029/) (2026) - [RAG-3DSG: Enhancing 3D Scene Graphs with Re-Shot Guided Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.10168/) (2026) - [See, Remember, Explore: A Benchmark and Baselines for Streaming Spatial Reasoning](https://mlsanity.com/paper/2603.23864/) (2026) - [Active Exploring like a Pigeon: Reinforcing Spatial Reasoning via Agentic Vision-Language Models](https://mlsanity.com/paper/2606.02459/) (2026) - [UniMesh: Unifying 3D Mesh Understanding and Generation](https://mlsanity.com/paper/2604.17472/) (2026) - [Thinking with Novel Views: A Systematic Analysis of Generative-Augmented Spatial Intelligence](https://mlsanity.com/paper/2605.10588/) (2026) - [Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial Reasoning](https://mlsanity.com/paper/2606.07436/) (2026) - [ScoutVLA: UAV-Centric Active Perception via a Dual-Expert VLA Model for Open-World Embodied Question Answering](https://mlsanity.com/paper/2606.14772/) (2026) - [Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation](https://mlsanity.com/paper/2610.20571/) (2026) ## Abstract (arXiv) Embodied question answering (EQA) in 3D environments often requires collecting context that is distributed across multiple viewpoints and partially occluded. However, most recent vision--language models (VLMs) are constrained to a fixed and finite set of input views, which limits their ability to acquire question-relevant context at inference time and hinders complex spatial reasoning. We propose Chain-of-View (CoV) prompting, a training-free, test-time reasoning framework that transforms a VLM into an active viewpoint reasoner through a coarse-to-fine exploration process. CoV first employs a View Selection agent to filter redundant frames and identify question-aligned anchor views. It then performs fine-grained view adjustment by interleaving iterative reasoning with discrete camera actions, obtaining new observations from the underlying 3D scene representation until sufficient context is gathered or a step budget is reached. We evaluate CoV on OpenEQA across four mainstream VLMs and obtain an average +11.56% improvement in LLM-Match, with a maximum gain of +13.62% on Qwen3-VL-Flash. CoV further exhibits test-time scaling: increasing the minimum action budget yields an additional +2.51% average improvement, peaking at +3.73% on Gemini-2.5-Flash. On ScanQA and SQA3D, CoV delivers strong performance (e.g., 116 CIDEr / 31.9 EM@1 on ScanQA and 51.1 EM@1 on SQA3D). Overall, these results suggest that question-aligned view selection coupled with open-view search is an effective, model-agnostic strategy for improving spatial reasoning in 3D EQA without additional training. Code is available on https://github.com/ziplab/CoV .