{"list":"closest","total":131,"rows":[{"id":"2608.16721","title":"GenRouter: Unified Workflow Routing for Agentic Image Generation","created":"2026-08-17","cited_by_count":5},{"id":"2608.13560","title":"AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design","created":"2026-08-13","cited_by_count":9},{"id":"2608.12313","title":"AVA-Encoder: Towards Agent-Native Video Representation Learning","created":"2026-08-12","cited_by_count":2},{"id":"2608.12290","title":"Beyond Trial-and-Error: Agentic Optimization for Image-to-Video Adherence","created":"2026-08-12","cited_by_count":1},{"id":"2608.06161","title":"iARCS: Iterative Agentic RL for Controllable 3D Scene Generation","created":"2026-08-06","cited_by_count":1},{"id":"2608.06075","title":"Domain-Grounded Candidate Selection for Agentic Image Editing: A Shadow Removal Case","created":"2026-08-06","cited_by_count":1},{"id":"2608.05485","title":"VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editing","created":"2026-08-06","cited_by_count":5},{"id":"2608.05248","title":"WorldClaw: Agentic 3D Open-World Generation at Scale","created":"2026-08-05","cited_by_count":8},{"id":"2608.04436","title":"ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation","created":"2026-08-05","cited_by_count":4},{"id":"2608.03298","title":"SeaSlides: Semantic Abstraction Layer for Agentic Slide Generation","created":"2026-08-04","cited_by_count":1},{"id":"2608.02218","title":"PosterMELD: Multi-Agent Paper-to-Poster Generation for Controllable Design Diversity with Editable Print-Ready Outputs","created":"2026-08-03","cited_by_count":1},{"id":"2608.00891","title":"CADIR: A Cross-Backend Editable Intermediate Representation for Agentic CAD Generation","created":"2026-08-01","cited_by_count":2},{"id":"2608.00548","title":"DrawAI: Agentic Benchmark and Workflow for Making Raster Images Editable","created":"2026-08-01","cited_by_count":1},{"id":"2607.27380","title":"VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System","created":"2026-07-29","cited_by_count":8},{"id":"2607.26910","title":"CinemaTraj: Composing Atomic Camera Trajectories for 3D Scenes with LLM Agents","created":"2026-07-29","cited_by_count":1},{"id":"2607.21522","title":"GS-Agent: Creating 4D Physical Worlds With Generative Simulation","created":"2026-07-23","cited_by_count":5},{"id":"2607.20866","title":"Agentic Designer: Progressive Multi-Agent Collaboration for Structure-Aware Interior Layout Generation","created":"2026-07-23","cited_by_count":1},{"id":"2607.19947","title":"ETPDesigner: Multi-Agent Orchestration for Interactive Multimodal Electronic Theater Program","created":"2026-07-22","cited_by_count":1},{"id":"2607.19038","title":"FilmWorld: Agentic Novel-to-Film Generation through Dynamic Cinematic World Modeling","created":"2026-07-21","cited_by_count":2},{"id":"2607.16355","title":"PhysAgent: Reflective Agentic Physics Control for Physically Plausible Video Generation","created":"2026-07-17","cited_by_count":2},{"id":"2607.13125","title":"Boogu-Image-0.1: Boosting Open Agentic Multimodal Generation via Understanding under a Minimal Budget","created":"2026-07-14","cited_by_count":6},{"id":"2607.12042","title":"SymbOmni: Evolving Agentic Omni Models via Symbolic Concept Learning","created":"2026-07-13","cited_by_count":2},{"id":"2607.05382","title":"Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation","created":"2026-07-06","cited_by_count":8},{"id":"2607.03731","title":"CoGen3D: An Agentic Human-AI Co-Design Pipeline for 3D Asset Generation for Virtual Reality","created":"2026-07-04","cited_by_count":1},{"id":"2607.01766","title":"SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation","created":"2026-07-02","cited_by_count":8},{"id":"2607.01102","title":"SAGE: Structured Agentic Graph Editing for Software Diagrams","created":"2026-07-01","cited_by_count":2},{"id":"2606.31154","title":"PPT-Eval: A Benchmark for Computer-Use Agents on PowerPoint Tasks","created":"2026-06-30","cited_by_count":7},{"id":"2606.30296","title":"ManimAgent: Self-Evolving Multimodal Agents for Visual Education","created":"2026-06-29","cited_by_count":2},{"id":"2606.29395","title":"NaLA: A 3D Native LLM Layout Agent for High-quality 3D Scene Generation","created":"2026-06-28","cited_by_count":2},{"id":"2606.28971","title":"Self-Evolving Agentic Image Restoration via Deliberate Planning and Intuitive Execution","created":"2026-06-27","cited_by_count":4},{"id":"2606.23221","title":"RS-Gen: A Multi-Stage Agentic Framework for Reasoning and Search-Augmented Image Generation","created":"2026-06-22","cited_by_count":7},{"id":"2606.20764","title":"One Image is All You Need: Agentic One-Shot Image Generation via Text-Based World Models for Long-Tail Spatial Perception","created":"2026-06-18","cited_by_count":1},{"id":"2606.19073","title":"Taming I2V models for Image HOI Editing: A Cognitive Benchmark and Agentic Self-Correcting Framework","created":"2026-06-17","cited_by_count":5},{"id":"2606.17536","title":"OmniDrive: An LLM-Choreographed Multi-Agent World Model with Unified Latent Co-Compression for Multi-View Driving Video Generation","created":"2026-06-16","cited_by_count":2},{"id":"2606.14168","title":"MUSE: Agentic 3D Scene Authoring via Memory-Grounded Incremental Requirement Satisfaction","created":"2026-06-12","cited_by_count":3},{"id":"2606.13679","title":"InterleaveThinker: Reinforcing Agentic Interleaved Generation","created":"2026-06-11","cited_by_count":2},{"id":"2606.09738","title":"HDSL: A Hierarchical Domain-Specific Language for Structured 3D Indoor Scene Generation and Localized Editing with LLM Agents","created":"2026-06-08","cited_by_count":2},{"id":"2606.08091","title":"VideoWeaver: Evaluating and Evolving Skills for Agentic Long Video Generation","created":"2026-06-06","cited_by_count":7},{"id":"2606.08016","title":"IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment","created":"2026-06-06","cited_by_count":2},{"id":"2606.05031","title":"MetaPoint: Unlocking Precise Spatial Control in Agentic Visual Generation","created":"2026-06-03","cited_by_count":4},{"id":"2606.07649","title":"ViMax: Agentic Video Generation","created":"2026-06-02","cited_by_count":12},{"id":"2606.01803","title":"OctoT2I: A Self-Evolving Agentic Text-to-Image Router","created":"2026-06-01","cited_by_count":5},{"id":"2606.01057","title":"3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code","created":"2026-05-31","cited_by_count":15},{"id":"2606.00204","title":"APE: Agentic Prompt Enhancer for Image Generation and Editing","created":"2026-05-29","cited_by_count":3},{"id":"2605.30248","title":"GenClaw: Code-Driven Agentic Image Generation","created":"2026-05-28","cited_by_count":11},{"id":"2605.30090","title":"DirectorBench: Diagnosing Long-Form Video Generation with Personalized Multi-Agent Evaluation","created":"2026-05-28","cited_by_count":4},{"id":"2605.28173","title":"MangaFlow: An End-to-End Agentic Framework for Controllable Story to Manga Generation","created":"2026-05-27","cited_by_count":1},{"id":"2605.28056","title":"CogPortrait: Fine-Grained Eye-Region Control in Portrait Animation via Hierarchical Agent Planning","created":"2026-05-27","cited_by_count":2},{"id":"2605.27705","title":"AgenticVBench: Can AI Agents Complete Real-World Post-Production Tasks?","created":"2026-05-26","cited_by_count":7},{"id":"2605.22645","title":"AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompters","created":"2026-05-21","cited_by_count":8},{"id":"2605.22144","title":"One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems","created":"2026-05-21","cited_by_count":6},{"id":"2605.18748","title":"Aurora: Unified Video Editing with a Tool-Using Agent","created":"2026-05-18","cited_by_count":9},{"id":"2605.18396","title":"NEWTON: Agentic Planning for Physically Grounded Video Generation","created":"2026-05-18","cited_by_count":12},{"id":"2605.17969","title":"Generation Navigator: A State-Aware Agentic Framework for Image Generation","created":"2026-05-18","cited_by_count":3},{"id":"2605.15187","title":"Articraft: An Agentic System for Scalable Articulated 3D Asset Generation","created":"2026-05-14","cited_by_count":30},{"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},{"id":"2605.07457","title":"EditRefiner: A Human-Aligned Agentic Framework for Image Editing Refinement","created":"2026-05-08","cited_by_count":1},{"id":"2605.01477","title":"Action Agent: Agentic Video Generation Meets Flow-Constrained Diffusion","created":"2026-05-02","cited_by_count":2},{"id":"2604.28185","title":"Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling","created":"2026-04-30","cited_by_count":5},{"id":"2604.25318","title":"Cutscene Agent: An LLM Agent Framework for Automated 3D Cutscene Generation","created":"2026-04-28","cited_by_count":3},{"id":"2604.24842","title":"Co-Director: Agentic Generative Video Storytelling","created":"2026-04-27","cited_by_count":3},{"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},{"id":"2604.22840","title":"AeSlides: Incentivizing Aesthetic Layout in LLM-Based Slide Generation via Verifiable Rewards","created":"2026-04-21","cited_by_count":11},{"id":"2604.16958","title":"Self-Reasoning Agentic Framework for Narrative Product Grid-Collage Generation","created":"2026-04-18","cited_by_count":1},{"id":"2604.15917","title":"Making Image Editing Easier via Adaptive Task Reformulation with Agentic Executions","created":"2026-04-17","cited_by_count":2},{"id":"2604.13452","title":"CANVAS: Continuity-Aware Narratives via Visual Agentic Storyboarding","created":"2026-04-15","cited_by_count":3},{"id":"2604.10383","title":"Authoring for Living Worlds: Tool-Constrained LLM Agents for Executable Multi-Actor Scenarios","created":"2026-04-11","cited_by_count":2},{"id":"2604.05076","title":"GLANCE: A Global-Local Coordination Multi-Agent Framework for Music-Grounded Non-Linear Video Editing","created":"2026-04-06","cited_by_count":2},{"id":"2603.29664","title":"CutClaw: Agentic Hours-Long Video Editing via Music Synchronization","created":"2026-03-31","cited_by_count":6},{"id":"2603.29620","title":"Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis","created":"2026-03-31","cited_by_count":17},{"id":"2603.28767","title":"Gen-Searcher: Reinforcing Agentic Search for Image Generation","created":"2026-03-30","cited_by_count":30},{"id":"2603.19708","title":"WorldAgents: Can Foundation Image Models be Agents for 3D World Models?","created":"2026-03-20","cited_by_count":2},{"id":"2603.18627","title":"Agentic Flow Steering and Parallel Rollout Search for Spatially Grounded Text-to-Image Generation","created":"2026-03-19","cited_by_count":1},{"id":"2603.16967","title":"MSRAMIE: Multimodal Structured Reasoning Agent for Multi-instruction Image Editing","created":"2026-03-17","cited_by_count":1},{"id":"2603.16839","title":"Learning to Present: Inverse Specification Rewards for Agentic Slide Generation","created":"2026-03-17","cited_by_count":2},{"id":"2603.12597","title":"Feynman: Knowledge-Infused Diagramming Agent for Scalable Visual Designs","created":"2026-03-13","cited_by_count":1},{"id":"2603.12310","title":"VQQA: An Agentic Approach for Video Evaluation and Quality Improvement","created":"2026-03-12","cited_by_count":12},{"id":"2603.12238","title":"SceneAssistant: A Visual Feedback Agent for Open-Vocabulary 3D Scene Generation","created":"2026-03-12","cited_by_count":6},{"id":"2603.12155","title":"GlyphBanana: Advancing Precise Text Rendering Through Agentic Workflows","created":"2026-03-12","cited_by_count":4},{"id":"2603.11048","title":"COMIC: Agentic Sketch Comedy Generation","created":"2026-03-11","cited_by_count":2},{"id":"2603.07148","title":"Agentic Planning with Reasoning for Image Styling via Offline RL","created":"2026-03-07","cited_by_count":1},{"id":"2603.02681","title":"VisionCreator: A Native Visual-Generation Agentic Model with Understanding, Thinking, Planning and Creation","created":"2026-03-03","cited_by_count":2},{"id":"2602.22839","title":"DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation","created":"2026-02-26","cited_by_count":18},{"id":"2602.19542","title":"Vinedresser3D: Agentic Text-guided 3D Editing","created":"2026-02-23","cited_by_count":3},{"id":"2604.09568","title":"EvoDiagram: Agentic Editable Diagram Creation via Design Expertise Evolution","created":"2026-02-20","cited_by_count":2},{"id":"2602.17558","title":"RetouchIQ: MLLM Agents for Instruction-Based Image Retouching with Generalist Reward","created":"2026-02-19","cited_by_count":4},{"id":"2602.14968","title":"PhyScensis: Physics-Augmented LLM Agents for Complex Physical Scene Arrangement","created":"2026-02-16","cited_by_count":7},{"id":"2602.11790","title":"Beyond End-to-End Video Models: An LLM-Based Multi-Agent System for Educational Video Generation","created":"2026-02-12","cited_by_count":4},{"id":"2602.10116","title":"SAGE: Scalable Agentic 3D Scene Generation for Embodied AI","created":"2026-02-10","cited_by_count":50},{"id":"2602.09153","title":"SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes","created":"2026-02-09","cited_by_count":46},{"id":"2602.09084","title":"Agent Banana: High-Fidelity Image Editing with Agentic Thinking and Tooling","created":"2026-02-09","cited_by_count":19},{"id":"2602.06166","title":"M3: High-fidelity Text-to-Image Generation via Multi-Modal, Multi-Agent and Multi-Round Visual Reasoning","created":"2026-02-05","cited_by_count":6},{"id":"2602.02051","title":"SIDiffAgent: Self-Improving Diffusion Agent","created":"2026-02-02","cited_by_count":1},{"id":"2602.01756","title":"Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generation","created":"2026-02-02","cited_by_count":23},{"id":"2601.22571","title":"PerfGuard: A Performance-Aware Agent for Visual Content Generation","created":"2026-01-30","cited_by_count":1},{"id":"2601.18543","title":"GenAgent: Scaling Text-to-Image Generation via Agentic Multimodal Reasoning","created":"2026-01-26","cited_by_count":24},{"id":"2601.17737","title":"The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation","created":"2026-01-25","cited_by_count":8},{"id":"2601.11109","title":"Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning","created":"2026-01-16","cited_by_count":49},{"id":"2601.09150","title":"World Craft: Agentic Framework to Create Visualizable Worlds via Text","created":"2026-01-14","cited_by_count":1},{"id":"2601.04794","title":"APEX: Academic Poster Editing Agentic Expert","created":"2026-01-08","cited_by_count":6}],"next_cursor":"100"}