mlsanityData to 14 Oct 2026

Visual Agentic AI for Spatial Reasoning with a Dynamic API

arXiv 2502.06787 ↗First posted 10 Feb 2025cs.CVcited by 43

On the map: LLM reasoning → Spatial and embodied reasoning

also in 1 more
Abstract (arXiv)

Visual reasoning -- the ability to interpret the visual world -- is crucial for embodied agents that operate within three-dimensional scenes. Progress in AI has led to vision and language models capable of answering questions from images. However, their performance declines when tasked with 3D spatial reasoning. To tackle the complexity of such reasoning problems, we introduce an agentic program synthesis approach where LLM agents collaboratively generate a Pythonic API with new functions to solve common subproblems. Our method overcomes limitations of prior approaches that rely on a static, human-defined API, allowing it to handle a wider range of queries. To assess AI capabilities for 3D understanding, we introduce a new benchmark of queries involving multiple steps of grounding and inference. We show that our method outperforms prior zero-shot models for visual reasoning in 3D and empirically validate the effectiveness of our agentic framework for 3D spatial reasoning tasks. Project website: https://glab-caltech.github.io/vadar/

Key facts. Cited by 43 papers in the map (data through 14 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 9 of its 45 references that are in the map. First posted on arXiv 10 Feb 2025.

Builds on

9 of 45 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces18 Dec
  2. 2023What's "up" with vision-language models? Investigating their struggle with spatial reasoning30 Oct

Other references · 7

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  4. 2023Gemini: A Family of Highly Capable Multimodal Modelscited by 872
  5. 2024Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Modelscited by 329
  6. 2021Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Conceptscited by 256
  7. 2024LAB-Bench: Measuring Capabilities of Language Models for Biology Researchcited by 156

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 21; 2026: 22.

43 papers.

Sort:

By area:

  1. 2025Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawingcited by 136
  2. 2025How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspectivecited by 43
  3. 20253D Aware Region Prompted Vision Language Modelcited by 33
  4. 2025SITE: towards Spatial Intelligence Thorough Evaluationcited by 29
  5. 2025Explain Before You Answer: A Survey on Compositional Visual Reasoningcited by 28
  6. 2026Think3D: Thinking with Space for Spatial Reasoningcited by 24
  7. 2025Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methodscited by 23
  8. 2025Is CLIP ideal? No. Can we fix it? Yes!cited by 21
  9. 2025ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric Videoscited by 21
  10. 2025SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RLcited by 21
  11. 2026SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoningcited by 17
  12. 2026pySpatial: Generating 3D Visual Programs for Zero-Shot Spatial Reasoningcited by 14
31 more
  1. 2025RefAV: Towards Planning-Centric Scenario Miningcited by 13
  2. 2025Euclid's Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate Taskscited by 13
  3. 2026S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligencecited by 11
  4. 2025Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMscited by 10
  5. 2026Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Drivingcited by 9
  6. 2026Agentic Retoucher for Text-To-Image Generationcited by 7
  7. 2025ESCA: Contextualizing Embodied Agents via Scene-Graph Generationcited by 6
  8. 2025SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learningcited by 6
  9. 2026Do MLLMs Really Understand Space? A Mathematical Reasoning Evaluationcited by 6
  10. 2026SUPERGLASSES: Benchmarking Vision Language Models as Intelligent Agents for AI Smart Glassescited by 6
  11. 2025Same or Not? Enhancing Visual Perception in Vision-Language Modelscited by 5
  12. 2025Aligning Text, Images, and 3D Structure Token-by-Tokencited by 4
  13. 2025No Labels, No Problem: Training Visual Reasoners with Multimodal Verifierscited by 4
  14. 2026Grounded 3D-Aware Spatial Vision-Language Modelingcited by 3
  15. 2025DocReward: A Document Reward Model for Structuring and Stylizingcited by 1
  16. 2025CompAgent: An Agentic Framework for Visual Compliance Verificationcited by 1
  17. 2026Playing ZendoWorld: Challenging AI Agents on Active Visual Concept Inductioncited by 1
  18. 2026SpatioLM: Towards General Physical Spatial Intelligence in Vision-Language Modelscited by 1
  19. 2025SpatialTraceGen: High-Fidelity Traces for Efficient VLM Spatial Reasoning Distillationcited by 0
  20. 2025The N-Body Problem: Parallel Execution from Single-Person Egocentric Videocited by 0
  21. 2026Global Commander and Local Operative: A Dual-Agent Framework for Scene Navigationcited by 0
  22. 2026Token Warping Helps MLLMs Look from Nearby Viewpointscited by 0
  23. 2026VTOS: Learning to Orchestrate Vision Tools by Co-Searching Solutions and Observerscited by 0
  24. 2026Accuracy and Cost Claims Do Not Survive Re-Execution in Agentic VideoQAcited by 0
  25. 2026R3D: Quantitative 3D Spatial Reasoning for Egocentric Wearablescited by 0
  26. 2026GaugeVLM: Structuring Spatial Supervision with Measured Geometric Interventionscited by 0
  27. 2026Agentic Relative Camera Pose Estimation via Learned Ranking and Verificationcited by 0
  28. 2026Uruqi: Learning Spatial Cognition from Visual Experiencecited by 0
  29. 2026From Reasoning Failures to Composable Video Spatial Intelligencecited by 0
  30. 2026Task-Adaptive Grounded 3D-Programmers Using 2D VLMscited by 0
  31. 2026EvoSpatial: Experience-Driven Skill and Tool Evolution for Spatial Reasoning Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026RieMind: Geometry-Grounded Spatial Agent for Scene Understanding
  2. 2025Pursuing Minimal Sufficiency in Spatial Reasoning
  3. 2026SpatiO: Adaptive Test-Time Orchestration of Vision-Language Agents for Spatial Reasoning
  4. 2026Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial Reasoning
  5. 2026From Perception to Action: Spatial AI Agents and World Models
  6. 2026Agentic AI with Structured CoT for Enhancing AI's Spatial Intelligence: Visualization and Reasoning of Rotation
  7. 2026Active Exploring like a Pigeon: Reinforcing Spatial Reasoning via Agentic Vision-Language Models
  8. 2025Geometrically-Constrained Agent for Spatial Reasoning