arXiv Computer Vision August 28, 2026 By Zaibin Zhang, Yuhan Wu, Lianjie Jia, Yifan Wang, Zhongbo Zhang, Yijiang Li, Binghao Ran, Fuxi Zhang, Zhuohan Sun, Yizhuang Peng, Zhenfei Yin, Lijun Wang, Huchuan Lu

Think3D: Thinking with Space for Spatial Reasoning

Read the original on arXiv Computer Vision →

Think3D introduces a framework that endows Vision‑Language Models with interactive 3D chain‑of‑thought reasoning by integrating 3D manipulation tools for active spatial exploration. The approach improves performance on benchmarks such as BLINK Multi‑view, MindCube‑1K, and VSI‑Bench‑Tiny for proprietary models like GPT‑4.1 and Gemini 2.5 Pro, and a reinforcement‑learning variant, Think3D‑RL, enables open‑weight models such as Qwen3‑VL‑4B to autonomously learn effective 3D exploration strategies, yielding tool‑use patterns comparable to stronger models and turning a performance drop on MindCube‑1K into a substantial improvement.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Computer Vision

Oct 16

Learning to Think and Explore in 3D World

The paper introduces ACT3D, a vision‑language model that learns to think and explore in 3D environments using only single‑image inputs and action‑based interactions. By fine‑tuning with trajectory supervision and then applying reinforcement learning driven by final‑answer correctness, ACT3D develops an exploration policy that adapts to the question and improves accuracy across six benchmarks, outperforming both proprietary and open‑source baselines while using fewer input frames. The study shows that outcome‑based RL can teach VLMs to decide when and how to acquire visual evidence, leading to better reasoning and spatial understanding.

By Yijiang Li, Bingyang Wang, Nuno Vasconcelos

llms reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Jun 12

Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoning

arXiv:2606. 12830v1 Announce Type: cross Abstract: While recent vision-language models (VLMs) demonstrate strong multimodal understanding, they remain limited in spatial reasoning tasks that require active evidence acquisition and multi-step visual interaction.

By Changye Li, Meng Lu, Yi Wu, Ligeng Zhu

llms agents multimodal benchmarks

arXiv AI

Jun 12

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

arXiv:2606. 13673v1 Announce Type: cross Abstract: Spatial reasoning, the ability to determine where objects are, how they relate, and how they move in 3D, remains a fundamental challenge for vision-language models (VLMs).

By Seokju Cho, Ryo Hachiuma, Abhishek Badki, Hang Su, Byung-Kwan Lee, Chan Hee Song, Sifei Liu, Subhashree Radhakrishnan, Seungryong Kim, Yu-Chiang Frank Wang, Min-Hung Chen

llms agents multimodal benchmarks

arXiv Computation and Language

6d ago

Humans in Space: Can MLLMs Construct Human-Centric Spatial Understanding via Active Exocentric Exploration?

arXiv:2610.34149v1 Announce Type: cross Abstract: While Multimodal Large Language Models (MLLMs) excel at zero-shot reasoning, their spatial capabilities are primarily evaluated through static, passi...

By Tianchen Guo, Tengyue Zhang, Chen Liu, Ling Chen, Xin Yu

llms fine-tuning multimodal benchmarks

arXiv AI

Jul 7

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

arXiv:2511. 07403v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language tasks, but continue to struggle with spatial reasoning.

By Hunar Batra, Haoqin Tu, Hardy Chen, Yuanze Lin, Cihang Xie, Ronald Clark

llms reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Aug 5

SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them

arXiv:2607. 27703v2 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly used in embodied agents to interpret visual inputs, reason about spatial relationships, and make task-level decisions based on that reasoning.

By Yang Zhou, Zixuan Huang, Sunzhu Li, Zhuo Yang, Chen Zhang, Shunian Chen, Caijun Yan, Jianyao Xu, Shunyu Liu, Weijie Fu, Peiliang Li, Xiaozhi Chen, Yuxiang Cai

llms agents computer-vision reinforcement-learning robotics fine-tuning multimodal benchmarks

One email a morning, machine-written

Related stories

Learning to Think and Explore in 3D World

Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoning

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

Humans in Space: Can MLLMs Construct Human-Centric Spatial Understanding via Active Exocentric Exploration?

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them