{"total":215,"rows":[{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191,"area":"agents"},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881,"area":"wm"},{"id":"2310.04406","title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","created":"2023-10-06","cited_by_count":574,"area":"lr"},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478,"area":"wm"},{"id":"2302.01560","title":"Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents","created":"2023-02-03","cited_by_count":398,"area":"agents"},{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345,"area":"offlinerl"},{"id":"2306.13831","title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","created":"2023-06-24","cited_by_count":327,"area":null},{"id":"2205.11495","title":"Flexible Diffusion Modeling of Long Videos","created":"2022-05-23","cited_by_count":294,"area":"diffusion"},{"id":"2311.05997","title":"JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models","created":"2023-11-10","cited_by_count":171,"area":"agents"},{"id":"2411.13543","title":"BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games","created":"2024-11-20","cited_by_count":146,"area":"lr"},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"id":"2305.10626","title":"Language Models Meet World Models: Embodied Experiences Enhance Language Models","created":"2023-05-18","cited_by_count":124,"area":"wm"},{"id":"2403.03186","title":"Cradle: Empowering Foundation Agents Towards General Computer Control","created":"2024-03-05","cited_by_count":117,"area":null},{"id":"2408.06327","title":"VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents","created":"2024-08-12","cited_by_count":103,"area":"mllm"},{"id":"2306.00937","title":"STEVE-1: A Generative Model for Text-to-Behavior in Minecraft","created":"2023-06-01","cited_by_count":97,"area":null},{"id":"2106.05963","title":"Learning to See by Looking at Noise","created":"2021-06-10","cited_by_count":92,"area":null},{"id":"2105.13231","title":"AndroidEnv: A Reinforcement Learning Platform for Android","created":"2021-05-27","cited_by_count":90,"area":null},{"id":"2301.12050","title":"Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling","created":"2023-01-28","cited_by_count":88,"area":"wm"},{"id":"2210.05359","title":"Mind's Eye: Grounded Language Model Reasoning through Simulation","created":"2022-10-11","cited_by_count":84,"area":"lr"},{"id":"2408.03615","title":"Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks","created":"2024-08-07","cited_by_count":84,"area":"agents"},{"id":"2404.10179","title":"Scaling Instructable Agents Across Many Simulated Worlds","created":"2024-03-13","cited_by_count":71,"area":null},{"id":"2312.07472","title":"MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception","created":"2023-12-12","cited_by_count":67,"area":null},{"id":"2312.09238","title":"Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft","created":"2023-12-14","cited_by_count":61,"area":null},{"id":"2106.12177","title":"Imitation Learning: Progress, Taxonomies and Challenges","created":"2021-06-23","cited_by_count":58,"area":"offlinerl"},{"id":"2311.15209","title":"See and Think: Embodied Agent in Virtual Environment","created":"2023-11-26","cited_by_count":54,"area":"lr"},{"id":"2403.12037","title":"MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control","created":"2024-03-18","cited_by_count":53,"area":"wm"},{"id":"2510.03198","title":"Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraft","created":"2025-10-03","cited_by_count":52,"area":"wm"},{"id":"2104.04258","title":"Counter-Strike Deathmatch with Large-Scale Behavioural Cloning","created":"2021-04-09","cited_by_count":50,"area":"offlinerl"},{"id":"2411.00114","title":"Project Sid: Many-agent simulations toward AI civilization","created":"2024-10-31","cited_by_count":49,"area":"wm"},{"id":"2602.22208","title":"Solaris: Building a Multiplayer Video World Model in Minecraft","created":"2026-02-25","cited_by_count":47,"area":"wm"},{"id":"2403.12014","title":"EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents","created":"2024-03-18","cited_by_count":46,"area":"agents"},{"id":"2310.13255","title":"Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds","created":"2023-10-20","cited_by_count":45,"area":"agents"},{"id":"2210.02396","title":"Temporally Consistent Transformers for Video Generation","created":"2022-10-05","cited_by_count":44,"area":null},{"id":"2102.09532","title":"Clockwork Variational Autoencoders","created":"2021-02-18","cited_by_count":42,"area":null},{"id":"2310.08235","title":"GROOT: Learning to Follow Instructions by Watching Gameplay Videos","created":"2023-10-12","cited_by_count":42,"area":null},{"id":"2101.11071","title":"The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors","created":"2021-01-26","cited_by_count":41,"area":null},{"id":"2301.10034","title":"Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction","created":"2023-01-21","cited_by_count":39,"area":null},{"id":"2505.21996","title":"VRAG: Learning World Models for Interactive Video Generation","created":"2025-05-28","cited_by_count":38,"area":"wm"},{"id":"2303.16563","title":"Skill Reinforcement Learning and Planning for Open-World Long-Horizon Tasks","created":"2023-03-29","cited_by_count":36,"area":null},{"id":"2106.14876","title":"Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft","created":"2021-06-28","cited_by_count":35,"area":null},{"id":"2310.08367","title":"MCU: An Evaluation Framework for Open-Ended Game Agents","created":"2023-10-12","cited_by_count":34,"area":null},{"id":"2402.19299","title":"RL-GPT: Integrating Reinforcement Learning and Code-as-policy","created":"2024-02-29","cited_by_count":32,"area":null},{"id":"2104.02710","title":"The Multi-Agent Behavior Dataset: Mouse Dyadic Social Interactions","created":"2021-04-06","cited_by_count":31,"area":null},{"id":"2512.04797","title":"SIMA 2: A Generalist Embodied Agent for Virtual Worlds","created":"2025-12-04","cited_by_count":31,"area":"agents"},{"id":"2204.08373","title":"Learning to Execute Actions or Ask Clarification Questions","created":"2022-04-18","cited_by_count":30,"area":null},{"id":"2312.00746","title":"Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Games","created":"2023-12-01","cited_by_count":30,"area":"agents"},{"id":"2407.00114","title":"OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents","created":"2024-06-27","cited_by_count":30,"area":"vla"},{"id":"2112.04907","title":"JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning","created":"2021-12-07","cited_by_count":28,"area":"offlinerl"},{"id":"2209.08483","title":"Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learning","created":"2022-09-18","cited_by_count":28,"area":null},{"id":"2307.10224","title":"RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization","created":"2023-07-15","cited_by_count":28,"area":null},{"id":"2503.16365","title":"JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse","created":"2025-03-20","cited_by_count":28,"area":"mllm"},{"id":"2601.02427","title":"NitroGen: An Open Foundation Model for Generalist Gaming Agents","created":"2026-01-04","cited_by_count":27,"area":"agents"},{"id":"2202.10583","title":"MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned","created":"2022-02-17","cited_by_count":26,"area":null},{"id":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"area":"offlinerl"},{"id":"2407.15325","title":"Odyssey: Empowering Minecraft Agents with Open-World Skills","created":"2024-07-22","cited_by_count":26,"area":"agents"},{"id":"2502.19902","title":"Optimus-2: Multimodal Minecraft Agent with Goal-Observation-Action Conditioned Policy","created":"2025-02-27","cited_by_count":25,"area":"agents"},{"id":"2210.06964","title":"Causality-driven Hierarchical Structure Discovery for Reinforcement Learning","created":"2022-10-13","cited_by_count":24,"area":null},{"id":"2312.02519","title":"Creative Agents: Empowering Agents with Imagination for Creative Tasks","created":"2023-12-05","cited_by_count":24,"area":"agents"},{"id":"2103.15332","title":"Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark","created":"2021-03-29","cited_by_count":23,"area":null},{"id":"2108.01069","title":"Self-Supervised Disentangled Representation Learning for Third-Person Imitation Learning","created":"2021-08-02","cited_by_count":23,"area":"offlinerl"},{"id":"2504.21853","title":"A Survey of Interactive Generative Video","created":"2025-04-30","cited_by_count":23,"area":null},{"id":"2402.04578","title":"S-Agents: Self-organizing Agents in Open-ended Environments","created":"2024-02-07","cited_by_count":22,"area":"agents"},{"id":"2203.16540","title":"Mind the gap: Challenges of deep learning approaches to Theory of Mind","created":"2022-03-30","cited_by_count":21,"area":null},{"id":"2310.08922","title":"LLaMA Rider: Spurring Large Language Models to Explore the Open World","created":"2023-10-13","cited_by_count":21,"area":null},{"id":"2107.08170","title":"Megaverse: Simulating Embodied Agents at One Million Experiences per Second","created":"2021-07-17","cited_by_count":20,"area":null},{"id":"2111.08857","title":"SEIHAI: A Sample-efficient Hierarchical AI for the MineRL Competition","created":"2021-11-17","cited_by_count":20,"area":"offlinerl"},{"id":"2211.07819","title":"General Intelligence Requires Rethinking Exploration","created":"2022-11-15","cited_by_count":20,"area":null},{"id":"2410.17856","title":"ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting","created":"2024-10-23","cited_by_count":20,"area":"mllm"},{"id":"2503.10704","title":"Error Analyses of Auto-Regressive Video Diffusion Models: A Unified Framework","created":"2025-03-12","cited_by_count":20,"area":"diffusion"},{"id":"2403.19267","title":"MineLand: Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical Needs","created":"2024-03-28","cited_by_count":18,"area":"agents"},{"id":"2107.04132","title":"A Systematic Survey of Text Worlds as Embodied Natural Language Environments","created":"2021-07-08","cited_by_count":17,"area":null},{"id":"2210.13417","title":"Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds","created":"2022-10-24","cited_by_count":17,"area":null},{"id":"2211.00539","title":"Dungeons and Data: A Large-Scale NetHack Dataset","created":"2022-11-01","cited_by_count":16,"area":"offlinerl"},{"id":"2402.07140","title":"Can Graph Descriptive Order Affect Solving Graph Problems with LLMs?","created":"2024-02-11","cited_by_count":16,"area":"lr"},{"id":"2412.21033","title":"Plancraft: an evaluation dataset for planning with LLM agents","created":"2024-12-30","cited_by_count":16,"area":"agents"},{"id":"2506.23046","title":"SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions","created":"2025-06-29","cited_by_count":16,"area":null},{"id":"2004.00981","title":"Benchmarking End-to-End Behavioural Cloning on Video Games","created":"2020-04-02","cited_by_count":15,"area":"offlinerl"},{"id":"2303.10571","title":"Reinforcement Learning Friendly Vision-Language Model for Minecraft","created":"2023-03-19","cited_by_count":14,"area":"mllm"},{"id":"2304.13269","title":"Games for Artificial Intelligence Research: A Review and Perspectives","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2312.08958","title":"LiFT: Unsupervised Reinforcement Learning with Foundation Models as Teachers","created":"2023-12-14","cited_by_count":14,"area":null},{"id":"2208.01174","title":"TextWorldExpress: Simulating Text Games at One Million Steps Per Second","created":"2022-08-01","cited_by_count":13,"area":null},{"id":"2403.07711","title":"SSM Meets Video Diffusion Models: Efficient Long-Term Video Generation with Structured State Spaces","created":"2024-03-12","cited_by_count":13,"area":"diffusion"},{"id":"2412.18293","title":"MineStudio: A Streamlined Package for Minecraft AI Agent Development","created":"2024-12-24","cited_by_count":13,"area":null},{"id":"2503.17359","title":"Position: Interactive Generative Video as Next-Generation Game Engine","created":"2025-03-21","cited_by_count":13,"area":null},{"id":"2506.10357","title":"Optimus-3: Dual-Router Aligned Mixture-of-Experts Agent with Dual-Granularity Reasoning-Aware Policy Optimization","created":"2025-06-12","cited_by_count":13,"area":"moe"},{"id":"2508.18722","title":"VistaWise: Building Cost-Effective Agent with Cross-Modal Knowledge Graph for Minecraft","created":"2025-08-26","cited_by_count":13,"area":"agents"},{"id":"2603.03482","title":"Beyond Pixel Histories: World Models with Persistent 3D State","created":"2026-03-03","cited_by_count":13,"area":"wm"},{"id":"2007.02701","title":"Scaling Imitation Learning in Minecraft","created":"2020-07-06","cited_by_count":12,"area":"offlinerl"},{"id":"2207.10553","title":"MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior","created":"2022-07-21","cited_by_count":12,"area":null},{"id":"2303.11191","title":"A Survey of Demonstration Learning","created":"2023-03-20","cited_by_count":12,"area":"offlinerl"},{"id":"2603.16871","title":"WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation","created":"2026-03-17","cited_by_count":12,"area":"wm"},{"id":"2312.01203","title":"Harnessing Discrete Representations For Continual Reinforcement Learning","created":"2023-12-02","cited_by_count":11,"area":"wm"},{"id":"2204.13022","title":"Binding Actions to Objects in World Models","created":"2022-04-27","cited_by_count":10,"area":"wm"},{"id":"2310.02505","title":"Learning to Reach Goals via Diffusion","created":"2023-10-04","cited_by_count":10,"area":"diffusion"},{"id":"2405.17424","title":"LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence","created":"2024-05-27","cited_by_count":10,"area":null},{"id":"2505.12707","title":"PLAICraft: Large-Scale Time-Aligned Vision-Speech-Action Dataset for Embodied AI","created":"2025-05-19","cited_by_count":10,"area":null},{"id":"2509.13347","title":"OpenHA: A Series of Open-Source Hierarchical Agentic Models in Minecraft","created":"2025-09-13","cited_by_count":10,"area":"agents"},{"id":"2206.00142","title":"IGLU Gridworld: Simple and Fast Environment for Embodied Dialog Agents","created":"2022-05-31","cited_by_count":9,"area":null},{"id":"2406.00024","title":"Embedding-Aligned Language Models","created":"2024-05-24","cited_by_count":9,"area":"alignment"},{"id":"2411.06736","title":"MrSteve: Instruction-Following Agents in Minecraft with What-Where-When Memory","created":"2024-11-11","cited_by_count":9,"area":"agents"}],"next_cursor":"100"}