{"total":97,"rows":[{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881,"area":"wm"},{"id":"2411.17465","title":"ShowUI: One Vision-Language-Action Model for GUI Visual Agent","created":"2024-11-26","cited_by_count":232,"area":null},{"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":"2401.03568","title":"Agent AI: Surveying the Horizons of Multimodal Interaction","created":"2024-01-07","cited_by_count":170,"area":"agents"},{"id":"2509.24527","title":"Training Agents Inside of Scalable World Models","created":"2025-09-29","cited_by_count":136,"area":"wm"},{"id":"2407.05996","title":"Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goals","created":"2024-07-08","cited_by_count":134,"area":"diffusion"},{"id":"2408.06327","title":"VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents","created":"2024-08-12","cited_by_count":103,"area":"mllm"},{"id":"2310.00166","title":"Motif: Intrinsic Motivation from Artificial Intelligence Feedback","created":"2023-09-29","cited_by_count":102,"area":null},{"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":"2406.04268","title":"Open-Endedness is Essential for Artificial Superhuman Intelligence","created":"2024-06-06","cited_by_count":80,"area":null},{"id":"2403.05313","title":"RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation","created":"2024-03-08","cited_by_count":75,"area":"lr"},{"id":"2310.08588","title":"Octopus: Embodied Vision-Language Programmer from Environmental Feedback","created":"2023-10-12","cited_by_count":73,"area":"mllm"},{"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":"2310.18308","title":"Gen2Sim: Scaling up Robot Learning in Simulation with Generative Models","created":"2023-10-27","cited_by_count":64,"area":null},{"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":"2310.08235","title":"GROOT: Learning to Follow Instructions by Watching Gameplay Videos","created":"2023-10-12","cited_by_count":42,"area":null},{"id":"2402.02651","title":"Vision-Language Models Provide Promptable Representations for Reinforcement Learning","created":"2024-02-05","cited_by_count":41,"area":"mllm"},{"id":"2404.19664","title":"Towards Generalist Robot Learning from Internet Video: A Survey","created":"2024-04-30","cited_by_count":40,"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":"2406.18043","title":"GenRL: Multimodal-foundation world models for generalization in embodied agents","created":"2024-06-26","cited_by_count":31,"area":"wm"},{"id":"2512.04797","title":"SIMA 2: A Generalist Embodied Agent for Virtual Worlds","created":"2025-12-04","cited_by_count":31,"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":"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":"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":"2312.02519","title":"Creative Agents: Empowering Agents with Imagination for Creative Tasks","created":"2023-12-05","cited_by_count":24,"area":"agents"},{"id":"2403.08282","title":"Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigation","created":"2024-03-13","cited_by_count":24,"area":"agents"},{"id":"2510.23691","title":"Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents","created":"2025-10-27","cited_by_count":24,"area":"agents"},{"id":"2403.10249","title":"A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challenges","created":"2024-03-15","cited_by_count":22,"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":"2404.04619","title":"Do We Really Need a Complex Agent System? Distill Embodied Agent into a Single Model","created":"2024-04-06","cited_by_count":19,"area":"agents"},{"id":"2504.05370","title":"EduPlanner: LLM-Based Multi-Agent Systems for Customized and Intelligent Instructional Design","created":"2025-04-07","cited_by_count":18,"area":"agents"},{"id":"2312.08958","title":"LiFT: Unsupervised Reinforcement Learning with Foundation Models as Teachers","created":"2023-12-14","cited_by_count":14,"area":null},{"id":"2406.11736","title":"Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Models","created":"2024-06-17","cited_by_count":14,"area":"synth"},{"id":"2401.16398","title":"Zero-shot Imitation Policy via Search in Demonstration Dataset","created":"2024-01-29","cited_by_count":13,"area":"offlinerl"},{"id":"2410.03618","title":"Open-World Reinforcement Learning over Long Short-Term Imagination","created":"2024-10-04","cited_by_count":13,"area":"wm"},{"id":"2412.18293","title":"MineStudio: A Streamlined Package for Minecraft AI Agent Development","created":"2024-12-24","cited_by_count":13,"area":null},{"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":"2402.01786","title":"COA-GPT: Generative Pre-trained Transformers for Accelerated Course of Action Development in Military Operations","created":"2024-02-01","cited_by_count":12,"area":null},{"id":"2308.07326","title":"AI Text-to-Behavior: A Study In Steerability","created":"2023-08-07","cited_by_count":11,"area":null},{"id":"2406.00120","title":"Reward Machines for Deep RL in Noisy and Uncertain Environments","created":"2024-05-31","cited_by_count":11,"area":"deeprl"},{"id":"2410.03450","title":"MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents","created":"2024-10-04","cited_by_count":11,"area":"agents"},{"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":"2411.06736","title":"MrSteve: Instruction-Following Agents in Minecraft with What-Where-When Memory","created":"2024-11-11","cited_by_count":9,"area":"agents"},{"id":"2411.18289","title":"Don't Let Your Robot be Harmful: Responsible Robotic Manipulation via Safety-as-Policy","created":"2024-11-27","cited_by_count":9,"area":null},{"id":"2412.10410","title":"GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents","created":"2024-12-07","cited_by_count":9,"area":null},{"id":"2505.22976","title":"LoopNav: Benchmarking Spatial Consistency in World Models","created":"2025-05-29","cited_by_count":9,"area":"wm"},{"id":"2312.02405","title":"BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks","created":"2023-12-05","cited_by_count":8,"area":null},{"id":"2404.08755","title":"Training a Vision Language Model as Smartphone Assistant","created":"2024-04-12","cited_by_count":8,"area":"mllm"},{"id":"2503.02505","title":"ROCKET-2: Steering Visuomotor Policy via Cross-View Goal Alignment","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2503.10684","title":"Open-World Skill Discovery from Unsegmented Demonstrations","created":"2025-03-11","cited_by_count":7,"area":null},{"id":"2607.11388","title":"StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structure","created":"2026-07-13","cited_by_count":7,"area":"mllm"},{"id":"2312.02312","title":"Visual Encoders for Data-Efficient Imitation Learning in Modern Video Games","created":"2023-12-04","cited_by_count":6,"area":"offlinerl"},{"id":"2410.03303","title":"SELU: Self-Learning Embodied MLLMs in Unknown Environments","created":"2024-10-04","cited_by_count":6,"area":"mllm"},{"id":"2405.15414","title":"Luban: Building Open-Ended Creative Agents via Autonomous Embodied Verification","created":"2024-05-24","cited_by_count":5,"area":"agents"},{"id":"2507.10741","title":"Ground-Compose-Reinforce: Grounding Language in Agentic Behaviours using Limited Data","created":"2025-07-14","cited_by_count":5,"area":"agents"},{"id":"2509.22170","title":"Leveraging LLM Agents for Automated Video Game Testing","created":"2025-09-26","cited_by_count":5,"area":"agents"},{"id":"2405.08037","title":"Layout Generation Agents with Large Language Models","created":"2024-05-13","cited_by_count":4,"area":"agents"},{"id":"2407.12161","title":"Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent","created":"2024-07-16","cited_by_count":4,"area":"agents"},{"id":"2408.01942","title":"Visual Grounding for Object-Level Generalization in Reinforcement Learning","created":"2024-08-04","cited_by_count":4,"area":"lr"},{"id":"2401.08525","title":"GATS: Gather-Attend-Scatter","created":"2024-01-16","cited_by_count":3,"area":null},{"id":"2503.24388","title":"RIG: Synergizing Reasoning and Imagination in End-to-End Generalist Policy","created":"2025-03-31","cited_by_count":3,"area":"wm"},{"id":"2505.18607","title":"From Entity-Centric to Goal-Oriented Graphs: Enhancing LLM Knowledge Retrieval in Minecraft","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2505.20148","title":"MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents","created":"2025-05-26","cited_by_count":3,"area":"agents"},{"id":"2507.23698","title":"Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents","created":"2025-07-31","cited_by_count":3,"area":"agents"},{"id":"2604.18975","title":"Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game","created":"2026-04-21","cited_by_count":3,"area":"agents"},{"id":"2605.09965","title":"Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2609.16679","title":"AI for Games in the Foundation Model Era","created":"2026-09-15","cited_by_count":3,"area":"wm"},{"id":"2602.02212","title":"MAIN-VLA: Modeling Abstraction of Intention and eNvironment for Vision-Language-Action Models","created":"2026-02-02","cited_by_count":2,"area":"vla"},{"id":"2406.02013","title":"Mamba as Decision Maker: Exploring Multi-scale Sequence Modeling in Offline Reinforcement Learning","created":"2024-06-04","cited_by_count":1,"area":"ssm"},{"id":"2409.03402","title":"Game On: Towards Language Models as RL Experimenters","created":"2024-09-05","cited_by_count":1,"area":null},{"id":"2411.17255","title":"APT: Architectural Planning and Text-to-Blueprint Construction Using Large Language Models for Open-World Agents","created":"2024-11-26","cited_by_count":1,"area":"agents"},{"id":"2502.13006","title":"Integrating Reinforcement Learning, Action Model Learning, and Numeric Planning for Tackling Complex Tasks","created":"2025-02-18","cited_by_count":1,"area":"offlinerl"},{"id":"2506.00814","title":"GuessBench: Sensemaking Multimodal Creativity in the Wild","created":"2025-06-01","cited_by_count":1,"area":"mllm"},{"id":"2508.13530","title":"CrafterDojo: A Suite of Foundation Models for Building Open-Ended Embodied Agents in Crafter","created":"2025-08-19","cited_by_count":1,"area":"agents"},{"id":"2510.16774","title":"Learning to play: A Multimodal Agent for 3D Game-Play","created":"2025-10-19","cited_by_count":1,"area":null},{"id":"2510.19892","title":"Can They Dixit? Yes they Can! Dixit as a Playground for Multimodal Language Model Capabilities","created":"2025-10-22","cited_by_count":1,"area":"mllm"},{"id":"2601.05215","title":"MineNPC-Task: Task Suite for Memory-Aware Minecraft Agents","created":"2026-01-08","cited_by_count":1,"area":"agents"},{"id":"2604.24697","title":"Can Current Agents Close the Discovery-to-Application Gap? A Case Study in Minecraft","created":"2026-04-27","cited_by_count":1,"area":"agents"},{"id":"2608.26200","title":"GameWAM: A World Action Model for Video Games","created":"2026-08-25","cited_by_count":1,"area":"wm"},{"id":"2410.18626","title":"SAMG: Offline-to-Online Reinforcement Learning via State-Action-Conditional Offline Model Guidance","created":"2024-10-24","cited_by_count":0,"area":"offlinerl"},{"id":"2412.00949","title":"STEVE-Audio: Expanding the Goal Conditioning Modalities of Embodied Agents in Minecraft","created":"2024-12-01","cited_by_count":0,"area":"agents"},{"id":"2412.16970","title":"A Research Agenda for Usability and Generalisation in Reinforcement Learning","created":"2024-12-22","cited_by_count":0,"area":"deeprl"},{"id":"2512.09706","title":"Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning","created":"2025-12-10","cited_by_count":0,"area":"agents"},{"id":"2603.13131","title":"MineEvolve: Self-Evolution with Accumulated Knowledge for Long-Horizon Embodied Minecraft Agents","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2605.13918","title":"CA2: Code-Aware Agent for Automated Game Testing","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.14211","title":"ASH: Agents that Self-Hone in Long-Horizon Worlds","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.23551","title":"Goal-Conditioned Agents that Learn Everything All at Once","created":"2026-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2606.00145","title":"Completion at the Boundary (CaB): Deployable Switching with Completion-Aware Control under Limited Calibration","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.12852","title":"WISE: A Long-Horizon Agent in Minecraft with Why-Which Reasoning","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2609.25001","title":"GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2610.13829","title":"MC-EvoBench: Auditing Experience-Driven Self-Improvement in Minecraft Agents","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.20240","title":"PAWA: Panoramic Action-conditioned World Modeling for Multiple Agents","created":"2026-10-14","cited_by_count":0,"area":"wm"}],"next_cursor":null}