All summaries

2026-11-13

• Lang-SVG: Hierarchical Image Vectorization with Language Priors Xi Liu, Chaoyi Zhou, Run Wang, et al. · arXiv:2611.15941

2026-11-11

• Seeing Isn't Enough: Unlocking Visual Reasoning by Bridging the Reasoning-Access Gap with TIGER Gregory Kang Ruey Lau, Minh Huynh Nguyen, Bryan Kian Hsiang Low · arXiv:2611.10552
• BIBIMBAP: A Benchmark for Instructional BIM-Based Automated Programming Clemens Kujat, Bharathi Kannan Nithyanantham, Stefan Telgmann, et al. · arXiv:2611.09933

2026-11-04

• Do Agentic Policies Need to Look at Every Step? Geometric Abstraction for Reasoning and Action Yihang Liu, Yiming Chen, Mingzhe Zheng · arXiv:2611.05058
• Intent2CAD: How Semantic-Parametric Supervision Shapes Text-to-CAD Generation Jinbo Yang, Mingyue Yuan, Shikai Jing · arXiv:2611.03449
• Ground-Wing: A Parametric 3D Wing-in-Ground-Effect Dataset for Benchmarking Neural Surrogate Models Andrea Cenzato, Lukas Karch, Andre Luckow, et al. · arXiv:2611.04571
• Composable CAD: Sketch-to-CAD Program Synthesis in Parts Yuan-Bo Li, Vivian Liu, Sean J. Liu, et al. · arXiv:2611.01165
• SketchMate: Agentic Geometric Reasoning for Zero-Shot Precision Insertion Jiaming Wang · arXiv:2610.41844

2026-11-03

• SpatialVec: A Unified Representation Learning Framework for Geospatial Objects with Boundary-Aware Sampling Samya Acharja, Kanchan Chowdhury · arXiv:2611.00111
• Parametric CAD Bench v3: Evaluating Agentic Parametric CAD Authoring from Text and Engineering Drawings Mei Chen, Yu Xia, Haipeng Mao · arXiv:2611.02659
• SketchBloom: Training-Free Vector Sketch Outpainting with Stroke-Level Style Control Quang-Thinh Nguyen, Duy-Khang Do, Tam V. Nguyen, et al. · arXiv:2611.00245

2026-10-31

• Decoding Geometry, Not Tokens: Efficient VLMs for Robot Affordance and Trajectory Prediction Akila Ayanthi, Darshana Priyasad, Tharindu Fernando, et al. · arXiv:2610.39416

2026-10-30

• CAD-WAM: Anticipating Geometry for Text-to-CAD Generation Zhengyang Li, Weijie Zheng, Yuxin Cui, et al. · arXiv:2610.39306

2026-10-28

• Zhengrong-Spatial-Aware 1.0: Advancing 3D Multimodal Intelligence Yu Zhang, Xiaogang Wang, Yuhang Cheng, et al. · arXiv:2610.37216
• Zooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal Perception Lai Wei, Yatai Li, Liangbo He, et al. · arXiv:2610.37037
• VibeVideoBench:Evaluating Multimodal Agents on Code-Driven Video Generation Mu-Xi Diao, Wen-Bin Xu, Le-Le Yang, et al. · arXiv:2610.35864

2026-10-23

• GraphCAD: Geometry-Aware Diffusion on Edge-Adjacency Graphs for CAD Generation Wenhao Zheng, Xianggen Liu, Li Yue, et al. · arXiv:2610.30974

2026-10-21

• S-Agent 2.0: Spatial Reasoning with a General Coding Agent Rui Gong, Ruoyu Wang, Yalun Dai, et al. · arXiv:2610.28354
• P$^3$-VLM: A Point-based Alternative for Grounded 3D Vision-Language Models Anna-Maria Halacheva, Jan-Nico Zaech, Sombit Dey, et al. · arXiv:2610.28018
• On the Limits of Scale: Inverse Scaling in Vision-Language Models Rohit Saxena, Alessandro Suglia, Marek Rei, et al. · arXiv:2610.27360
• Where is Physical RSI capability from? An Observational Scaling Law of LLM-as-policy Ze-Kai Li, Jia-Yi Yu, Jin-Lu Zhang, et al. · arXiv:2610.26848
• HexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding Agents Hong-Cheng Gao, Alex Zhou, Jay Zhu, et al. · arXiv:2610.23479

2026-10-16

• DeSpatial: The devil of Agentic Spatial Reasoning Lies in 3D Itself Yifei Liu, Xiaolong Zhou, Ziyang Gong, et al. · arXiv:2610.20990

2026-10-14

• Rethinking Human Intent-to-CAD: Parametric CAD Model Generation via Cooperative Multi-Task Alignment and Spatial-Aware Reinforcement Learning Qingwang Zhang, Jiahao Li, Xiangdong Zhou · arXiv:2610.15681
• LayerCanvas: Infographic Generation in AI Learning Assistants via Hybrid Layer-Set Diffusion Keshav Gupta, Jeremy Owen, Christopher Lloyd, et al. · arXiv:2610.18763

2026-10-12

• A Real-World CAD Segmentation Benchmark: Comparing Rule-Based and Learning-Based Approaches through Hole Detection Kai Schütte, Edgar Heinert, Matthias Rottmann · arXiv:2610.13466

2026-10-08

• Flow-of-Thought: A Framework for Visual Reasoning Mariia Baidachna, Nicolas Pugeault · arXiv:2610.09746
• GeoWM: Efficient Direct World Modeling in Explicit Geometry Mehrdad Noori, Gui-Le Wu, S. Hosseini, et al. · arXiv:2610.07381

2026-10-07

• 2D Spatial Reasoning with Adaptive Neural Cellular Automata Martin Spitznagel, Janis Keuper · arXiv:2610.08518
• PrimitiveCAD: An LLM-Based Point-to-CAD Reconstruction with Primitive-Aware Tokenization and Operation Alignment Jian Gao, Kailin Bi, Jiamin Xu, et al. · arXiv:2610.08698

2026-10-06

• SpatialChain: A Benchmark for Auditing Spatial Reasoning Faithfulness in VLMs Rafael Teixeira Sousa, Vinícius Paulo Lopes de Oliveira, Elisa Ayumi Masasi de Oliveira, et al. · arXiv:2610.06413
• UniBRep: Learning Unified Geometry and Topology for Image-conditioned B-Rep Generation Haiyang Ying, Allen Tu, Jiaye Wu, et al. · arXiv:2610.04092
• CADDreamer: CAD Object Generation from Single-view Images Unknown authors · arXiv:2502.20732

2026-10-05

• IGNITE Tokamak World Model Architecture Peter Steiner, Azarakhsh Jalalvand, Nathaniel Chen, et al. · arXiv:2610.02515
• Windfoil: Closed-Form Coverage for Real-Time and Differentiable Vector Graphics Matt DesLauriers · arXiv:2610.02468

2026-10-03

• Task-Adaptive Grounded 3D-Programmers Using 2D VLMs Arman Raayatsanati, Sombit Dey, Anna-Maria Halacheva, et al. · arXiv:2610.02021
• World Motion Models: Flexible Sequence Modeling of SE(3) Trajectories Jia-Hui Lei, Qian-Qian Wang, Trevor Darrell, et al. · arXiv:2610.01742

2026-10-02

• GeoLatent: Geometry-Guided Latent Structuring with Routed Optimization for 3D Reasoning Yakun Zhu, Yi Bin, Yujuan Ding, et al. · arXiv:2610.02091
• From Reasoning Failures to Composable Video Spatial Intelligence Pengzhan Sun, Junbin Xiao, Ramanathan Rajaraman, et al. · arXiv:2610.01999
• Does Learning Protein Folding Generalize to Broader Reasoning? Yong Liu, Zhan-Peng Shi, Yi-Zhou Dang, et al. · arXiv:2609.38879

2026-09-30

• Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering Jaewoo Jung, Hyeonseo Yu, Honggyu An, et al. · arXiv:2609.38177
• Code4Scene: Benchmarking Coding Agents for Constructing and Editing 3D Scenes Xiaokang Ye, Siddhant Hitesh Mantri, Zimeng Chen, et al. · arXiv:2609.36777
• Back2Struct: Making Structured Images Editable Again Pengyu Yan, Yixin Wu, Yunjie Tian, et al. · arXiv:2609.37016
• Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence Hong-Cheng Gao, Jing-Jing Zhou, Ze Zheng, et al. · arXiv:2609.35432
• Geometric Encoding for Spatial Reasoning in Vision-Language Models Antonio Jun, Hao-Shui Yu, Zheng-Yi Lu, et al. · arXiv:2609.34148
• What Stops Recursive Self-Improvement in Robotics? Lessons from 123 Rounds of Agentic Skill Discovery Jia-Ming Wang · arXiv:2609.31760

2026-09-29

• Hard Vision, Easy Vision: What GPT-6 Astra Reveals Across Computer Vision Hanoona Rasheed, Mohammed Irfan Kurpath, Bin Ren, et al. · arXiv:2609.35718
• Who Is Left of Whom? Tracing Spatial Evidence and Role Binding in Relative-Position Reasoning Yingjin Song, Denis Paperno, Albert Gatt · arXiv:2609.35486
• Test-Time Spatial Reasoning for Robot Manipulation Using Generative Real-to-Sim Ivan Kapelyukh, Yafei Hu, Ran Gong, et al. · arXiv:2609.33982
• SphMind: Towards Robust, Training-Free VLM-based Spatial Reasoning with a 360 Camera Shriram Damodaran, Soumyaratna Debnath, Cheston Tan, et al. · arXiv:2609.33462
• ConCAD: Constraint-Aware Image-to-CAD Generation with Dual-Granularity Rewards Chenxi Zhai, Xi Cheng, Hang Cheng, et al. · arXiv:2609.34494
• RoGSW4RLD: Feed-Forward 4D Gaussian Lifting for Robot World Model Rollouts Jin Hyun Kim, Min Young Kim, Soohwan Song, et al. · arXiv:2609.35311
• Does Learning to Predict the World Help Agents Act? Auditing World-Model Post-Training Xinyu Che, Hang Yan, Yanchen Liu, et al. · arXiv:2609.33335
• World Agent: Can Language Models Keep a World Running? Weixing Chen, Weipeng Zhang, Nan An, et al. · arXiv:2609.32692
• GameBoyWorlds: A Testbed for Self-Improvement in Embodied Video Games Dhananjay Ashok, Adam Shen, Aslan Huo Feng, et al. · arXiv:2609.32093
• HapticWorld: an Interactive World Simulator with Real-time Torque Feedback Shaoting Peng, Litian Liang, Yixuan Wang, et al. · arXiv:2609.31924
• DrawingsDreamer: A Unified Multi-View Engineering Drawings Generation Model Shurui Liu, Weide Chen, Changwang Yi, et al. · arXiv:2609.35242

2026-09-26

• Free the Language Model From the Vision Encoder: Semantic Serialization as a Perception Interface for Small Language Models Cong Xu, Ravi Sankar · arXiv:2609.29601
• AgenticCADedit: A Stateful, Tool-Mediated Agentic Approach to Multimodal 3D CAD Editing Saptarshi Neil Sinha, Mika Silvan Goschke, P. Kühn, et al. · arXiv:2609.29621

2026-09-25

• Beyond Spatial Benchmarks: From Spatial Reasoning to Navigation Xun Huang, Shijia Zhao, Rongsheng Qu, et al. · arXiv:2609.29934

2026-09-24

• SurgGraph: Quantitative Laparoscopic Video Understanding via Geometry-Grounded Scene Graphs Jing-Ying Wang, Rosiana Natalie, Marquise D. Singleterry, et al. · arXiv:2609.25651

2026-09-23

• VGGT-CAD: Reconstructing Parametric CAD 3D Model with Geometric Grounding Chunan Yu, Tianrun Chen, Fu Shen, et al. · arXiv:2609.21225
• Benchmarking World Models for Continual Learning on Compositional Tasks Haoyu Zhou, Joe Watson, Anson Lei, et al. · arXiv:2609.22055
• How unconstrained machine-learning models learn physical symmetries M. Domina, Joseph W Abbott, Paolo Pegolo, et al. · arXiv:2603.24638
• INTCORT: Training-Free Spatial Reasoning Enhancement for Vision-Language Models via Input Transformations and Confidence Routing Haoran Sun, Jingqi Xu, Yanhui Li, et al. · arXiv:2609.24813
• Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World Kaixiang Yao, Xu Wang, Miao Pan, et al. · arXiv:2609.23038
• Vision2CAD: A Visual Agent Harness for Explicit Geometry Referencing and Localization in Parametric CAD Modeling Xi Cheng, Chenxi Zhai, Hang Cheng, et al. · arXiv:2609.22688
• Fysiverse-3D-Vision Technical Report: Generating Executable 3D Worlds from Images through Unified Spatial Reasoning Dingkang Yang, Yizhou Liu, Wendong Cheng, et al. · arXiv:2609.25741
• RULER: Instance-aware Rubric Rewards for SVG Generation Hangyu Ran, Yuhao Zheng, Yingying Zhang, et al. · arXiv:2609.25270
• Latent Telepathy: Multi-Robot Communication with Self-Supervised Perceptual Latents Howard Wang, Han Zheng, Cathy Wu · arXiv:2609.23269

2026-09-19

• Coding Agents with an Obstacle-Aware Harness for Safe Robot Manipulation Bing-Xin Xu, Yu-Zhang Shang, Zhen-Han Dong, et al. · arXiv:2609.20822

2026-09-17

• HistCAD: A Constraint-Aware Parametric History-Based CAD Representation, Dataset, and Benchmark with Industrial Complexity Unknown authors · arXiv:2602.19171
• Zero-to-CAD: Agentic Synthesis of Interpretable CAD Programs at Million-Scale Without Real Data Unknown authors · arXiv:2604.24479
• DeepCAD: A Deep Generative Network for Computer-Aided Design Models Unknown authors · arXiv:2105.09492
• CADFS: A Big CAD Program Dataset and Framework for Computer-Aided Design with Large Language Models Unknown authors · arXiv:2605.01925
• JoinABLe: Learning Bottom-up Assembly of Parametric CAD Joints Unknown authors · arXiv:2111.12772
• Computer-Aided Design as Language Yaroslav Ganin, Sergey Bartunov, Yujia Li, et al. · arXiv:2105.02769
• SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Design Ari Seff, Yaniv Ovadia, Wenda Zhou, et al. · arXiv:2007.08506
• www.ijcai.org/proceedings/2023/0200.pdf Unknown authors · arXiv:url-063ea42052b9ee84
• EDCT-Bench: Uncovering Faithfulness Gaps in VLMs via Explanation-Driven Counterfactual Testing Sihao Ding, Santosh Vasa, Aditi Ramadwar, et al. · arXiv:2609.17953
• UAVs Meet Embodied Intelligence: Bridging Human Intents and Flying Dynamics Via Harnessing Physical-Digital AI Agents Yonglin Tian, Weiyi Wang, Houhua Lu, et al. · arXiv:2609.18326
• SparseTalk - Sparsifying 3D Gaussian Language Fields for Efficient 3D Visual Question Answering Davit Soselia, J. Jaja, Amitabh Varshney · arXiv:2609.15137

2026-09-16

• Compositional SVG Generation via VLM-Driven Hierarchical Semantic Parsing Sehwan Park, Taehoon Kim, Geonhee Han, et al. · arXiv:2609.14657

2026-09-11

• Code World Model: Coding Agent as World Brain Yiwen Chen, Guosheng Lin, Chi Zhang · arXiv:2608.25927
• HiFi-BRep: High-Fidelity Latent Representation for Robust B-Rep Generation Junhao Hou, Chenqi Luo, Pufan Wang, et al. · arXiv:2608.16485
• Spatially Aware World Action Model via Geometric Latent Diffusion Javier Alejandro Lopetegui Gonzalez, Paul Pacaud, Cordelia Schmid · arXiv:2609.02531
• Solaris: Towards Interfaces That Are Generated, Not Coded Yuval Alaluf, Omri Avrahami, Guy Bukchin Leshem, et al. · arXiv:2609.00776
• Deploying and Evaluating a Smart-Agriculture Agentic Engine for Full-Season Soybean Farm Operations Ao Qu, Panagiotis Michelakis, Linyuan Han, et al. · arXiv:2609.00106
• SVG-Score: Human-Aligned Evaluation of Text-to-SVG Generation Marco Cipriano, Leonardo Zini, Alexandra Schild, et al. · arXiv:2609.03806
• 3DHarnessBench: Probing Agentic 3D-to-Code Capabilities of Frontier Vision-Language Models Unknown authors · arXiv:2609.06535
• MindTopo: Can Foundation Models Reason in Topological Space? Yunfei Ge, Anbang Liu, Qineng Wang, et al. · arXiv:2609.11900
• Learn the Solid, Not the File: Canonical Inputs for Neural Networks on CAD Boundary Representations Heinrich Jiang, Hager Yasser Mohamed, Alexander Hitt, et al. · arXiv:2609.11573

2026-09-10

• MM-SVGEdit: A Multimodal-Driven SVG Editing for UI Design Shibo Yang, Yuqing Gao, Zipeng Liu · arXiv:2609.06116
• CIT-CAD: Constraint Intent Tree-based CAD Code Generation and Verification Unknown authors · arXiv:2609.07434

2026-09-04

• GraFT: A Training-Free Framework for Spatial Reasoning in Multimodal Large Language Models via 3D Scene Graphs Junqing Du, Fernando Ropero, Erkin Turkoz, et al. · arXiv:2609.03892
• Unfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning Yijun Yang, Shenghe Zheng, Wenbo Li, et al. · arXiv:2609.03729

2026-09-03

• Projector Is All You Train Nyx Iskandar, Saathvik Selvan, Slater Victoroff · arXiv:2608.19726
• Toward AI-Friendly Cartography: Understanding How Color Design Influences Foundation Model Spatial Reasoning on Sequential Choropleth Maps Yonghe Sun, Zhenjia Liu, Hua Liao, et al. · arXiv:2608.15736
• IterCAD: Iterative Program Repair for CAD Code Generation from Orthographic Views Yuchuan Wu, Ke Niu, Haiyang Yu, et al. · arXiv:2608.24020
• MIRAGE-CAD: Construction-Mediated Multimodal Generation of Executable CAD Programs Jizong Zhan · arXiv:2608.28669
• Dutch Books for Language Models Isaiah Andrews, Suproteem Sarkar · arXiv:2609.02797
• Towards a Belief-Based World Model for LLM Agents Shubham Kumar, Harshit Kumar, Narendra Ahuja, et al. · arXiv:2609.00455