Complete research index
AI agents that create artifacts.
Browse all 257 papers on AI agents for artifact creation, with authors, publication venues, original papers, and code.
Generated from the same audited dataset as the interactive catalog. Each record links to its original source. Download JSON.
Textual Artifacts (35)
-
SystemProfiliTable
ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows
-
SystemThe AI Scientist
Towards end-to-end automation of AI research
-
SystemDeepTutor
DeepTutor: Towards Agentic Personalized Tutoring
-
SystemMulti-Agent Comedy Club
Multi-Agent Comedy Club: Investigating Community Discussion Effects on LLM Creative Writing
-
BenchmarkMLR-Bench
MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research
2D Visual Artifacts (61)
-
BenchmarkSciFlow-Bench
SciFlow-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing
-
SystemPreference-Guided Prompt Optimization
Preference-Guided Prompt Optimization for Text-to-Image Generation
-
SystemAgentic Retoucher
Agentic Retoucher for Text-To-Image Generation
-
BenchmarkP2PEval
P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark
-
BenchmarkDV-World
DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios
-
SystemPaperBanana
PaperBanana: Automating Academic Illustration for AI Scientists
-
SystemAgent Banana
Agent Banana: High-Fidelity Image Editing with Agentic Thinking and Tooling
-
SystemGenAI-DrawIO-Creator
GenAI-DrawIO-Creator: A Framework for Automated Diagram Generation
-
SystemArcDeck
Narrative-Driven Paper-to-Slide Generation via ArcDeck
-
BenchmarkSlidesGen-Bench
SlidesGen-Bench: Evaluating Slides Generation via Computational and Quantitative Metrics
-
BenchmarkDiagramGenBenchmark
From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and Editing
-
SystemSketchAgent
SketchAgent: Language-Driven Sequential Sketch Generation
-
SystemBannerAgency
BannerAgency: Advertising Banner Design with Multimodal LLM Agents
-
SystemMulti-turn Consistent Image Editing
Multi-turn Consistent Image Editing
-
SystemSketchAgent
SketchAgent: Generating Structured Diagrams from Hand-Drawn Sketches
-
System4KAgent
4KAgent: Agentic Any Image to 4K Super-Resolution
-
BenchmarkGraphicBench
GraphicBench: A Planning Benchmark for Graphic Design with Language Agents
-
SystemCompositional Neural Painter
Stroke-based Neural Painting and Stylization with Dynamically Predicted Painting Region
Audio Artifacts (11)
-
SystemLibretto
Libretto: Giving LLM Agents a Sense of Musical Structure
-
BenchmarkRIME
RIME: Enabling Large-Scale Agentic Music Post-Production
-
SystemCoComposer
CoComposer: LLM Multi-agent Collaborative Music Composition
-
SystemMusicSwarm
MusicSwarm: Biologically Inspired Intelligence for Music Composition
Video Artifacts (34)
-
SystemCode2Video
Code2Video: A Code-centric Paradigm for Educational Video Creation
-
SystemVideoAgent
VideoAgent: Personalized Synthesis of Scientific Videos
-
SystemManimAgent
ManimAgent: Self-Evolving Multimodal Agents for Visual Education
-
SystemParticleGen
ParticleGen: A Multi-Agent System for Particle Effects Generation
-
SystemVideoMemory
VideoMemory: Toward Consistent Video Generation via Memory Integration
-
SystemEditDuet
EditDuet: A Multi-Agent System for Video Non-Linear Editing
-
SystemPaperTalker
Paper2Video: Automatic Video Generation from Scientific Papers
Spatial Artifacts (35)
-
SystemCode2Worlds
Code2Worlds: Empowering Coding LLMs for 4D World Generation
-
SystemDebate2Create
Debate2Create: Robot Co-design via Multi-Agent LLM Debate
-
SystemSceneSmith
SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes
-
SystemWorldAgents
WorldAgents: Can Foundation Image Models be Agents for 3D World Models?
-
SystemSceneGenAgent
SceneGenAgent: Precise Industrial Scene Generation with Coding Agent
-
SystemLL3M
LL3M: Large Language 3D Modelers
-
SystemChat-Edit-3D
Chat-Edit-3D: Interactive 3D Scene Editing via Text Prompts
-
SystemSceneCraft
SceneCraft: An LLM Agent for Synthesizing 3D Scenes as Blender Code
Behavioral Artifacts (74)
-
BenchmarkCodeFlowBench
CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation
-
SystemInfiniteWeb
InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training
-
BenchmarkGameDevBench
GameDevBench: Evaluating Agentic Capabilities Through Game Development
-
BenchmarkNL2Repo-Bench
NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents
-
BenchmarkProxyWar
ProxyWar: Dynamic Assessment of LLM Code Generation in Game Arenas
-
BenchmarkProductWebGen
ProductWebGen: Benchmarking Multimodal Product Webpage Generation
-
SystemAgentic Real2Sim
Agentic Real2Sim: Physics-based World Modeling with Vision-Language Agents
-
BenchmarkBackendForge
BackendForge: Benchmarking Agentic End-to-End Code Generation with Backend Services
-
SystemComfySearch
ComfySearch: Autonomous Exploration and Reasoning for ComfyUI Workflows
-
SystemLingBot-World 2.0
Infinite Worlds with Versatile Interactions
-
SystemOpenGame
OpenGame: Open Agentic Coding for Games
-
SystemSketch2Simulation
Sketch2Simulation: Automating Flowsheet Generation via Multi Agent Large Language Models
-
SystemDreamGarden
DreamGarden: A Designer Assistant for Growing Games from a Single Prompt
-
SystemAFlow
AFlow: Automating Agentic Workflow Generation
-
SystemMeta Agent Search
Automated Design of Agentic Systems
-
BenchmarkScienceAgentBench
ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
-
SystemAutoML-Agent
AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML
-
BenchmarkPaperBench
PaperBench: Evaluating AI’s Ability to Replicate AI Research
-
SystemLessons Learned
Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and Improve
-
BenchmarkWebCode2M
WebCode2M: A Real-World Dataset for Code Generation from Webpage Designs
-
SystemCoder-CUA Collaboration
Computer-Use Agents as Judges for Generative User Interface
-
BenchmarkSWE-bench
SWE-bench: Can Language Models Resolve Real-world Github Issues?
-
BenchmarkMLAgentBench
MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation
Unclassified (7)
-
SystemResearchStudio-Reel
ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog
About the survey and citation · Audit methodology · CC BY 4.0