{"total":134,"rows":[{"id":"2505.02836","title":"Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation","created":"2025-05-05","cited_by_count":67,"area":"agents"},{"id":"2509.20414","title":"SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent","created":"2025-09-24","cited_by_count":56,"area":"agents"},{"id":"2405.10255","title":"When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models","created":"2024-05-16","cited_by_count":43,"area":"mllm"},{"id":"2411.16602","title":"Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models","created":"2024-11-25","cited_by_count":38,"area":"diffusion"},{"id":"2410.16770","title":"The Scene Language: Representing Scenes with Programs, Words, and Embeddings","created":"2024-10-22","cited_by_count":36,"area":null},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2504.01786","title":"BlenderGym: Benchmarking Foundational Model Systems for Graphics Editing","created":"2025-04-02","cited_by_count":31,"area":null},{"id":"2501.12909","title":"FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces","created":"2025-01-22","cited_by_count":28,"area":"agents"},{"id":"2411.02394","title":"AutoVFX: Physically Realistic Video Editing from Natural Language Instructions","created":"2024-11-04","cited_by_count":27,"area":null},{"id":"2503.14756","title":"SceneEval: Evaluating Semantic Coherence in Text-Conditioned 3D Indoor Scene Synthesis","created":"2025-03-18","cited_by_count":26,"area":null},{"id":"2503.04919","title":"FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placement","created":"2025-03-06","cited_by_count":25,"area":"lr"},{"id":"2407.11965","title":"UrbanWorld: An Urban World Model for 3D City Generation","created":"2024-07-16","cited_by_count":24,"area":"wm"},{"id":"2503.16848","title":"HSM: Hierarchical Scene Motifs for Multi-Scale Indoor Scene Generation","created":"2025-03-21","cited_by_count":24,"area":null},{"id":"2505.05474","title":"3D Scene Generation: A Survey","created":"2025-05-08","cited_by_count":24,"area":"diffusion"},{"id":"2412.17811","title":"ChatGarment: Garment Estimation, Generation and Editing via Large Language Models","created":"2024-12-23","cited_by_count":23,"area":"mllm"},{"id":"2407.21333","title":"Chat2Layout: Interactive 3D Furniture Layout with a Multimodal LLM","created":"2024-07-31","cited_by_count":21,"area":"mllm"},{"id":"2508.08228","title":"LL3M: Large Language 3D Modelers","created":"2025-08-11","cited_by_count":20,"area":null},{"id":"2506.23329","title":"IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering","created":"2025-06-29","cited_by_count":19,"area":"mllm"},{"id":"2511.16825","title":"WorldGen: From Text to Traversable and Interactive 3D Worlds","created":"2025-11-20","cited_by_count":19,"area":null},{"id":"2602.11757","title":"Code2Worlds: Empowering Coding LLMs for 4D World Generation","created":"2026-02-12","cited_by_count":19,"area":null},{"id":"2605.09423","title":"SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning","created":"2026-05-10","cited_by_count":17,"area":"agents"},{"id":"2408.10453","title":"Kubrick: Multimodal Agent Collaborations for Synthetic Video Generation","created":"2024-08-19","cited_by_count":16,"area":"agents"},{"id":"2410.12836","title":"EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing","created":"2024-10-03","cited_by_count":15,"area":null},{"id":"2508.05899","title":"HOLODECK 2.0: Vision-Language-Guided 3D World Generation with Editing","created":"2025-08-07","cited_by_count":15,"area":null},{"id":"2606.01057","title":"3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code","created":"2026-05-31","cited_by_count":15,"area":"agents"},{"id":"2506.07570","title":"OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization","created":"2025-06-09","cited_by_count":14,"area":"synth"},{"id":"2509.14981","title":"SPATIALGEN: Layout-guided 3D Indoor Scene Generation","created":"2025-09-18","cited_by_count":14,"area":null},{"id":"2508.14893","title":"Virtual Community: An Open World for Humans, Robots, and Society","created":"2025-08-20","cited_by_count":13,"area":null},{"id":"2503.11060","title":"BannerAgency: Advertising Banner Design with Multimodal LLM Agents","created":"2025-03-14","cited_by_count":11,"area":null},{"id":"2605.19587","title":"SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated Objects","created":"2026-05-19","cited_by_count":11,"area":null},{"id":"2502.13372","title":"MoVer: Motion Verification for Motion Graphics Animations","created":"2025-02-19","cited_by_count":10,"area":"mllm"},{"id":"2506.07217","title":"BIMgent: Towards Autonomous Building Modeling via Computer-use Agents","created":"2025-06-08","cited_by_count":10,"area":"agents"},{"id":"2508.05580","title":"Follow-Your-Instruction: A Comprehensive MLLM Agent for World Data Synthesis","created":"2025-08-07","cited_by_count":10,"area":"mllm"},{"id":"2604.23580","title":"PhysCodeBench: Benchmarking Physics-Aware Symbolic Simulation of 3D Scenes via Self-Corrective Multi-Agent Refinement","created":"2026-04-26","cited_by_count":10,"area":"agents"},{"id":"2408.08054","title":"Text2BIM: Generating Building Models Using a Large Language Model-based Multi-Agent Framework","created":"2024-08-15","cited_by_count":9,"area":"agents"},{"id":"2506.22291","title":"RoomCraft: Controllable and Complete 3D Indoor Scene Generation","created":"2025-06-27","cited_by_count":9,"area":null},{"id":"2604.02580","title":"VoxelCodeBench: Benchmarking 3D World Modeling Through Code Generation","created":"2026-04-02","cited_by_count":8,"area":"wm"},{"id":"2607.01766","title":"SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation","created":"2026-07-02","cited_by_count":8,"area":"agents"},{"id":"2608.05248","title":"WorldClaw: Agentic 3D Open-World Generation at Scale","created":"2026-08-05","cited_by_count":8,"area":"agents"},{"id":"2411.18807","title":"Reconstructing Animals and the Wild","created":"2024-11-27","cited_by_count":7,"area":null},{"id":"2412.15200","title":"DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation","created":"2024-12-19","cited_by_count":7,"area":null},{"id":"2506.17450","title":"BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing","created":"2025-06-20","cited_by_count":7,"area":null},{"id":"2405.20319","title":"ParSEL: Parameterized Shape Editing with Language","created":"2024-05-30","cited_by_count":6,"area":null},{"id":"2507.14841","title":"Towards Geometric and Textural Consistency 3D Scene Generation via Single Image-guided Model Generation and Layout Optimization","created":"2025-07-20","cited_by_count":6,"area":null},{"id":"2508.18597","title":"SemLayoutDiff: Semantic Layout Generation with Diffusion Model for Indoor Scene Synthesis","created":"2025-08-26","cited_by_count":6,"area":"diffusion"},{"id":"2510.02178","title":"DisCo-Layout: Disentangling and Coordinating Semantic and Physical Refinement in a Multi-Agent Framework for 3D Indoor Layout Synthesis","created":"2025-10-02","cited_by_count":6,"area":"agents"},{"id":"2511.20415","title":"MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and Layouts","created":"2025-11-25","cited_by_count":6,"area":"wm"},{"id":"2601.17717","title":"A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data","created":"2026-01-25","cited_by_count":6,"area":"synth"},{"id":"2603.12238","title":"SceneAssistant: A Visual Feedback Agent for Open-Vocabulary 3D Scene Generation","created":"2026-03-12","cited_by_count":6,"area":"agents"},{"id":"2607.22393","title":"SceneActBench: Can Agents Act on the 3D Scenes They See?","created":"2026-07-24","cited_by_count":6,"area":"mllm"},{"id":"2609.15478","title":"BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender","created":"2026-09-14","cited_by_count":6,"area":"diffusion"},{"id":"2506.09656","title":"Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives","created":"2025-06-11","cited_by_count":5,"area":"agents"},{"id":"2509.05263","title":"LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation","created":"2025-09-05","cited_by_count":5,"area":"wm"},{"id":"2602.05362","title":"Imagine a City: CityGenAgent for Procedural 3D City Generation","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2604.22984","title":"BrickNet: Graph-Backed Generative Brick Assembly","created":"2026-04-24","cited_by_count":5,"area":null},{"id":"2607.21522","title":"GS-Agent: Creating 4D Physical Worlds With Generative Simulation","created":"2026-07-23","cited_by_count":5,"area":"agents"},{"id":"2504.15049","title":"ScanEdit: Hierarchically-Guided Functional 3D Scan Editing","created":"2025-04-21","cited_by_count":4,"area":null},{"id":"2505.21079","title":"Uni3D-MoE: Scalable Multimodal 3D Scene Understanding via Mixture of Experts","created":"2025-05-27","cited_by_count":4,"area":"mllm"},{"id":"2512.22351","title":"VULCAN: Tool-Augmented Multi Agents for Iterative 3D Object Arrangement","created":"2025-12-26","cited_by_count":4,"area":"mllm"},{"id":"2605.07342","title":"Mage: Multi-Axis Evaluation of LLM-Generated Executable Game Scenes Beyond Compile-Pass Rate","created":"2026-05-08","cited_by_count":4,"area":null},{"id":"2607.08970","title":"MultiView-Bench: A Diagnostic Benchmark for World-Centric Multi-View Integration in VLMs","created":"2026-07-09","cited_by_count":4,"area":null},{"id":"2608.26238","title":"Procedura: Agentic 3D Modeling with Procedural Control","created":"2026-08-26","cited_by_count":4,"area":"agents"},{"id":"2502.07128","title":"Cardiverse: Harnessing LLMs for Novel Card Game Prototyping","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2505.15765","title":"Constructing a 3D Scene from a Single Image","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2507.06484","title":"3D-Generalist: Self-Improving Vision-Language-Action Models for Crafting 3D Worlds","created":"2025-07-09","cited_by_count":3,"area":"lr"},{"id":"2510.04536","title":"3Dify: a Framework for Procedural 3D-CG Generation Assisted by LLMs Using MCP and RAG","created":"2025-10-06","cited_by_count":3,"area":null},{"id":"2510.17603","title":"ShapeCraft: LLM Agents for Structured, Textured and Interactive 3D Modeling","created":"2025-10-20","cited_by_count":3,"area":"agents"},{"id":"2512.08905","title":"Self-Evolving 3D Scene Generation from a Single Image","created":"2025-12-09","cited_by_count":3,"area":null},{"id":"2512.17445","title":"LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents","created":"2025-12-19","cited_by_count":3,"area":null},{"id":"2512.24986","title":"PhysTalk: Language-driven Real-time Physics in 3D Gaussian Scenes","created":"2025-12-31","cited_by_count":3,"area":null},{"id":"2602.19542","title":"Vinedresser3D: Agentic Text-guided 3D Editing","created":"2026-02-23","cited_by_count":3,"area":"agents"},{"id":"2604.03315","title":"StoryBlender: Inter-Shot Consistent and Editable 3D Storyboard with Spatial-temporal Dynamics","created":"2026-04-01","cited_by_count":3,"area":null},{"id":"2604.10578","title":"Rein3D: Reinforced 3D Indoor Scene Generation with Panoramic Video Diffusion Models","created":"2026-04-12","cited_by_count":3,"area":"diffusion"},{"id":"2605.12449","title":"LychSim: A Controllable and Interactive Simulation Framework for Vision Research","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2609.11499","title":"Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs","created":"2026-09-10","cited_by_count":3,"area":"wm"},{"id":"2504.00185","title":"Self-Evolving Visual Concept Library using Vision-Language Critics","created":"2025-03-31","cited_by_count":2,"area":"synth"},{"id":"2511.05533","title":"MCP4IFC: IFC-Based Building Design Using Large Language Models","created":"2025-10-29","cited_by_count":2,"area":null},{"id":"2602.04053","title":"Seeing Through Clutter: Structured 3D Scene Reconstruction via Iterative Object Removal","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2603.22972","title":"WorldMesh: Generating Navigable Multi-Room 3D Scenes via Mesh-Conditioned Image Diffusion","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2604.13035","title":"SceneCritic: A Symbolic Evaluator for 3D Indoor Scene Synthesis","created":"2026-04-14","cited_by_count":2,"area":"mllm"},{"id":"2604.19907","title":"SceneOrchestra: Efficient Agentic 3D Scene Synthesis via Full Tool-Call Trajectory Generation","created":"2026-04-21","cited_by_count":2,"area":"agents"},{"id":"2605.12586","title":"3D Primitives are a Spatial Language for VLMs","created":"2026-05-12","cited_by_count":2,"area":"mllm"},{"id":"2607.16355","title":"PhysAgent: Reflective Agentic Physics Control for Physically Plausible Video Generation","created":"2026-07-17","cited_by_count":2,"area":"agents"},{"id":"2607.22738","title":"Nova3D: Code-Native Generation of Programmable 3D Assets","created":"2026-07-22","cited_by_count":2,"area":null},{"id":"2608.15265","title":"VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End?","created":"2026-08-15","cited_by_count":2,"area":"agents"},{"id":"2409.10090","title":"InteractPro: A Unified Framework for Motion-Aware Image Composition","created":"2024-09-16","cited_by_count":1,"area":null},{"id":"2503.02595","title":"StageDesigner: Artistic Stage Generation for Scenography via Theater Scripts","created":"2025-03-04","cited_by_count":1,"area":"diffusion"},{"id":"2508.08821","title":"3DFroMLLM: 3D Prototype Generation only from Pretrained Multimodal LLMs","created":"2025-08-12","cited_by_count":1,"area":"mllm"},{"id":"2601.05016","title":"From Idea to Co-Creation: A Planner-Actor-Critic Framework for Agent Augmented 3D Modeling","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2601.12234","title":"Proc3D: Procedural 3D Generation and Parametric Editing of 3D Shapes with Large Language Models","created":"2026-01-18","cited_by_count":1,"area":null},{"id":"2601.14602","title":"3D Space as a Scratchpad for Editable Text-to-Image Generation","created":"2026-01-21","cited_by_count":1,"area":"lr"},{"id":"2601.19433","title":"RoamScene3D: Immersive Text-to-3D Scene Generation via Adaptive Object-aware Roaming","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2603.29301","title":"Self-Consistency for LLM-Based Motion Trajectory Generation and Verification","created":"2026-03-31","cited_by_count":1,"area":"lr"},{"id":"2604.15951","title":"Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval","created":"2026-04-17","cited_by_count":1,"area":"lr"},{"id":"2604.16552","title":"Co-generation of Layout and Shape from Text via Autoregressive 3D Diffusion","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2604.26509","title":"3D Generation for Embodied AI and Robotic Simulation: A Survey","created":"2026-04-29","cited_by_count":1,"area":null},{"id":"2605.25326","title":"Perceive-then-Plan: Layout-as-Policy for Monocular 3D Scene Layout Estimation","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2605.30326","title":"RoboWits: Unexpected Challenges for Robotic Creative Problem Solving","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.10478","title":"3D-CoS: A New 3D Reconstruction Paradigm Based on VLM Code Synthesis","created":"2026-06-09","cited_by_count":1,"area":null}],"next_cursor":"100"}