When faced with complex spatial problems, humans naturally sketch layouts to organize their thinking, and the act of drawing further sharpens their understanding. In this work, we ask whether a similar principle holds for Large Language Models (LLMs): can learning to construct explicit visual layouts from spatial descriptions instill genuine spatial understanding? We introduce Text2Space, a dataset that pairs natural language descriptions with ground-truth ASCII grid layouts and spatial QA pairs, enabling us to separate failures in constructing spatial representations from failures in reasoning over them. We adopt ASCII because it is human-readable, operates entirely within the token space of language models, and encodes spatial relations in a structurally verifiable form. Our evaluation reveals a pronounced "Read-Write Asymmetry": LLMs interpret ASCII representations effectively but struggle to produce them from text, and these construction errors propagate to incorrect answers downstream. To address this limitation, we train models on layout construction (Text$\rightarrow$ASCII) and find that it significantly improves spatial reasoning from text alone, even without producing any ASCII at inference time. Combining construction with comprehension training further amplifies these gains. Crucially, these improvements transfer to three external spatial reasoning benchmarks, demonstrating that, much as sketching sharpens human spatial thinking, learning to construct explicit layouts instills spatial understanding that generalizes beyond the training format.
Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);Ant Group(蚂蚁集团);CUHK MMLab(香港中文大学MMLab);Nanjing University(南京大学)
Testing the Depth of ChatGPT's Comprehension via Cross-Modal Tasks Based on ASCII-Art: GPT3.5's Abilities in Regard to Recognizing and Generating ASCII-Art Are Not Totally Lacking
Context-Aware Mapping of 2D Drawing Annotations to 3D CAD Features Using LLM-Assisted Reasoning for Manufacturing Automation
Singapore Institute of Manufacturing Technology (SIMTech), A*STAR, Singapore(新加坡制造技术研究所);Advanced Remanufacturing and Technology Centre (ARTC), A*STAR, Singapore(先进再制造与技术中心);School of Mechanical and Aerospace Engineering, Nanyang Technological University(机械与航空航天工程学院)
Partial Reasoning in Language Models: Search and Refinement Guided by Uncertainty
Advanced Knowledge Center for Immersive Technologies (AKCIT)(沉浸式技术高级知识中心);Federal University of Goiás, Brazil(巴西戈亚斯联邦大学);OATML, University of Oxford(牛津大学OATML)
Draw with Thought: Unleashing Multimodal Reasoning for Scientific Diagram Generation
Nanjing University of Information Science \& Technology Nanjing China;East China Normal University Shanghai China;The Hong Kong University of Science;Brown University Providence America;Southwest Jiaotong University Chengdu China;Nanjing University of Information Science \& Technology;East China Normal University;Brown University;Southwest Jiaotong University
提出无需训练的框架Draw with Thought,通过认知思维链推理将科学图表重建为可编辑的mxGraph XML代码,并发布Plot2XML基准,实验证明该方法能生成高保真且结构有效的重建结果。
Design-to-Plan: A Large Language Model-Based Multi-Agent Framework for Manufacturing Process Planning from 3D CAD Models and 2D Engineering Drawings
Singapore Institute of Manufacturing Technology (SIMTech), Agency for Science, Technology and Research (A*STAR)(新加坡制造技术研究院(新加坡科学、技术与研究局));Advanced Remanufacturing and Technology Centre (ARTC), Agency for Science, Technology and Research (A*STAR)(先进再制造与技术中心(新加坡科学、技术与研究局));School of Mechanical and Aerospace Engineering, Nanyang Technological University(南洋理工大学机械与宇航工程学院)
MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding
Beijing Academy of Artificial Intelligence (BAAI), China(北京人工智能研究院);Institute of Information Engineering, Chinese Academy of Sciences, China(信息工程研究所);Beijing University of Technology, China(北京理工大学)
SridBench: Benchmark of Scientific Research Illustration Drawing of Image Generation Model
University of Science and Technology of China(中国科学技术大学);Shanghai Innovation Institute(上海创新研究院);Nankai University(南开大学);Wuhan University(武汉大学);Shanghai AI Laboratory(上海人工智能实验室)
E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoning
Fudan University(复旦大学);Brain Technologies, Inc.(脑技术公司);South China University of Technology(华南理工大学);ByteDance AI Lab(字节跳动人工智能实验室);University of California Santa Barbara(加州大学圣巴巴拉分校);Fudan-Aishu Cognitive Intelligence Joint Research Center(复旦-爱数认知智能联合研究中心)
Unlocking the Working Memory of Large Language Models for Latent Reasoning
ELLIS Unit Linz and LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria(林茨ELLIS单元和LIT AI实验室,机器学习研究所,约翰·凯撒大学林茨,奥地利);NXAI GmbH, Linz, Austria(NXAI公司,林茨,奥地利)
A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning
Institute for Artificial Intelligence, Tsinghua University(清华大学人工智能研究院);Beijing National Research Center for Information Science and Technology(北京信息科学与技术国家研究中心);Tencent AI Lab(腾讯AI实验室)