SOTAVerified

Minecraft

Papers

Showing 150 of 236 papers

TitleStatusHype
Matrix-Game: Interactive World Foundation ModelCode5
Voyager: An Open-Ended Embodied Agent with Large Language ModelsCode5
Mastering Diverse Domains through World ModelsCode4
MineDojo: Building Open-Ended Embodied Agents with Internet-Scale KnowledgeCode4
Parallelized Planning-Acting for Efficient LLM-based Multi-Agent SystemsCode3
MineStudio: A Streamlined Package for Minecraft AI Agent DevelopmentCode3
Odyssey: Empowering Minecraft Agents with Open-World SkillsCode3
Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement LearningCode3
Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online VideosCode3
WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM AgentsCode2
AssistanceZero: Scalably Solving Assistance GamesCode2
Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon TasksCode2
Craftium: An Extensible Framework for Creating Reinforcement Learning EnvironmentsCode2
VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in MinecraftCode2
MineLand: Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical NeedsCode2
MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World ControlCode2
Octopus: Embodied Vision-Language Programmer from Environmental FeedbackCode2
STEVE-1: A Generative Model for Text-to-Behavior in MinecraftCode2
Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and MemoryCode2
Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task AgentsCode2
Temporally Consistent Transformers for Video GenerationCode2
Toward Memory-Aided World Models: Benchmarking via Spatial ConsistencyCode1
MineAnyBuild: Benchmarking Spatial Planning for Open-world AI AgentsCode1
Plancraft: an evaluation dataset for planning with LLM agentsCode1
TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in MinecraftCode1
ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context PromptingCode1
IDAT: A Multi-Modal Dataset and Toolkit for Building and Evaluating Interactive Task-Solving AgentsCode1
Playing NetHack with LLMs: Potential & Limitations as Zero-Shot AgentsCode1
S-Agents: Self-organizing Agents in Open-ended EnvironmentsCode1
ReGAL: Refactoring Programs to Discover Generalizable AbstractionsCode1
MinePlanner: A Benchmark for Long-Horizon Planning in Large Minecraft WorldsCode1
Creative Agents: Empowering Agents with Imagination for Creative TasksCode1
BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy TasksCode1
Convolutional State Space Models for Long-Range Spatiotemporal ModelingCode1
Towards Evaluating Generalist Agents: An Automated Benchmark in Open WorldCode1
Large Language Model (LLM) as a System of Multiple Expert Agents: An Approach to solve the Abstraction and Reasoning Corpus (ARC) ChallengeCode1
SmartPlay: A Benchmark for LLMs as Intelligent AgentsCode1
Semantic HELM: A Human-Readable Memory for Reinforcement LearningCode1
SPRING: Studying the Paper and Reasoning to Play GamesCode1
When and What to Ask Through World States and Text Instructions: IGLU NLP Challenge SolutionCode1
Reinforcement Learning Friendly Vision-Language Model for MinecraftCode1
Evolving Flying Machines in Minecraft Using Quality DiversityCode1
Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World ModellingCode1
Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon PredictionCode1
Craft an Iron Sword: Dynamically Generating Interactive Game Characters by Prompting Large Language Models Tuned on CodeCode1
Learning Controllable 3D Level GeneratorsCode1
Learning to Execute Actions or Ask Clarification QuestionsCode1
Combining Learning from Human Feedback and Knowledge Engineering to Solve Hierarchical Tasks in MinecraftCode1
ProTo: Program-Guided Transformer for Program-Guided TasksCode1
MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative TasksCode1
Show:102550
← PrevPage 1 of 5Next →

No leaderboard results yet.