{"total":192,"rows":[{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407,"area":null},{"id":"2303.17491","title":"Language Models can Solve Computer Tasks","created":"2023-03-30","cited_by_count":372,"area":null},{"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":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292,"area":null},{"id":"2302.02662","title":"Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning","created":"2023-02-06","cited_by_count":195,"area":null},{"id":"2306.00958","title":"LIV: Language-Image Representations and Rewards for Robotic Control","created":"2023-06-01","cited_by_count":188,"area":null},{"id":"2212.10789","title":"Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editing","created":"2022-12-21","cited_by_count":166,"area":null},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"area":null},{"id":"2305.11854","title":"Multimodal Web Navigation with Instruction-Finetuned Foundation Models","created":"2023-05-19","cited_by_count":160,"area":null},{"id":"2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","created":"2023-05-30","cited_by_count":147,"area":null},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138,"area":null},{"id":"2403.03186","title":"Cradle: Empowering Foundation Agents Towards General Computer Control","created":"2024-03-05","cited_by_count":117,"area":null},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2310.00166","title":"Motif: Intrinsic Motivation from Artificial Intelligence Feedback","created":"2023-09-29","cited_by_count":102,"area":null},{"id":"2406.06769","title":"DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents","created":"2024-06-10","cited_by_count":100,"area":null},{"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":"2403.16971","title":"AIOS: LLM Agent Operating System","created":"2024-03-25","cited_by_count":97,"area":null},{"id":"2403.01038","title":"AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks","created":"2024-03-02","cited_by_count":96,"area":null},{"id":"2306.09200","title":"ChessGPT: Bridging Policy Learning and Language Modeling","created":"2023-06-15","cited_by_count":75,"area":null},{"id":"2404.10179","title":"Scaling Instructable Agents Across Many Simulated Worlds","created":"2024-03-13","cited_by_count":71,"area":null},{"id":"2306.01711","title":"OMNI: Open-endedness via Models of human Notions of Interestingness","created":"2023-06-02","cited_by_count":70,"area":null},{"id":"2308.01399","title":"Learning to Model the World with Language","created":"2023-07-31","cited_by_count":68,"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":"2304.07297","title":"Language Instructed Reinforcement Learning for Human-AI Coordination","created":"2023-04-13","cited_by_count":63,"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":"2405.10315","title":"TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction","created":"2024-05-16","cited_by_count":59,"area":null},{"id":"2407.10943","title":"GRUtopia: Dream General Robots in a City at Scale","created":"2024-07-15","cited_by_count":59,"area":null},{"id":"2310.08586","title":"PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm","created":"2023-10-12","cited_by_count":56,"area":null},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2302.04449","title":"Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals","created":"2023-02-09","cited_by_count":45,"area":null},{"id":"2402.02500","title":"Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning","created":"2024-02-04","cited_by_count":45,"area":null},{"id":"2403.17918","title":"AgentStudio: A Toolkit for Building General Virtual Agents","created":"2024-03-26","cited_by_count":45,"area":null},{"id":"2308.12270","title":"Language Reward Modulation for Pretraining Reinforcement Learning","created":"2023-08-23","cited_by_count":43,"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":"2310.09971","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","created":"2023-10-15","cited_by_count":41,"area":null},{"id":"2404.19664","title":"Towards Generalist Robot Learning from Internet Video: A Survey","created":"2024-04-30","cited_by_count":40,"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":"2409.17115","title":"Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale","created":"2024-09-25","cited_by_count":37,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"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":"2401.14151","title":"True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning","created":"2024-01-25","cited_by_count":36,"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":"2304.09349","title":"LLM as A Robotic Brain: Unifying Egocentric Memory and Control","created":"2023-04-19","cited_by_count":33,"area":null},{"id":"2304.10750","title":"Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback","created":"2023-04-21","cited_by_count":32,"area":null},{"id":"2307.00117","title":"Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control","created":"2023-06-30","cited_by_count":32,"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":"2403.09142","title":"USimAgent: Large Language Models for Simulating Search Users","created":"2024-03-14","cited_by_count":32,"area":null},{"id":"2305.13246","title":"Interactive Natural Language Processing","created":"2023-05-22","cited_by_count":31,"area":null},{"id":"2305.18090","title":"ChatGPT-powered Conversational Drug Editing Using Retrieval and Domain Feedback","created":"2023-05-29","cited_by_count":31,"area":null},{"id":"2403.00025","title":"On the Challenges and Opportunities in Generative AI","created":"2024-02-28","cited_by_count":31,"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":"2402.01704","title":"Steering Language Models with Game-Theoretic Solvers","created":"2024-01-24","cited_by_count":28,"area":null},{"id":"2306.11886","title":"SPRINT: Scalable Policy Pre-Training via Language Instruction Relabeling","created":"2023-06-20","cited_by_count":24,"area":null},{"id":"2404.17521","title":"Ag2Manip: Learning Novel Manipulation Skills with Agent-Agnostic Visual and Action Representations","created":"2024-04-26","cited_by_count":24,"area":null},{"id":"2412.08542","title":"MaestroMotif: Skill Design from Artificial Intelligence Feedback","created":"2024-12-11","cited_by_count":24,"area":null},{"id":"2403.07548","title":"Online Continual Learning For Interactive Instruction Following Agents","created":"2024-03-12","cited_by_count":22,"area":null},{"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":"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":"2405.10020","title":"Natural Language Can Help Bridge the Sim2Real Gap","created":"2024-05-16","cited_by_count":21,"area":null},{"id":"2412.05255","title":"TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft","created":"2024-12-06","cited_by_count":21,"area":null},{"id":"2211.07819","title":"General Intelligence Requires Rethinking Exploration","created":"2022-11-15","cited_by_count":20,"area":null},{"id":"2310.08348","title":"LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios","created":"2023-10-12","cited_by_count":20,"area":null},{"id":"2306.13945","title":"Large Sequence Models for Sequential Decision-Making: A Survey","created":"2023-06-24","cited_by_count":19,"area":null},{"id":"2211.03959","title":"Pretraining in Deep Reinforcement Learning: A Survey","created":"2022-11-08","cited_by_count":18,"area":null},{"id":"2307.07909","title":"Is Imitation All You Need? Generalized Decision-Making with Dual-Phase Training","created":"2023-07-16","cited_by_count":18,"area":null},{"id":"2311.00344","title":"A Definition of Open-Ended Learning Problems for Goal-Conditioned Agents","created":"2023-11-01","cited_by_count":18,"area":null},{"id":"2306.09312","title":"Semantic HELM: A Human-Readable Memory for Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2404.15538","title":"DreamCraft: Text-Guided Generation of Functional 3D Environments in Minecraft","created":"2024-04-23","cited_by_count":17,"area":null},{"id":"2507.03253","title":"RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs","created":"2025-07-04","cited_by_count":17,"area":null},{"id":"2304.10782","title":"Contrastive Language, Action, and State Pre-training for Robot Learning","created":"2023-04-21","cited_by_count":16,"area":null},{"id":"2305.06289","title":"Learning Video-Conditioned Policies for Unseen Manipulation Tasks","created":"2023-05-10","cited_by_count":16,"area":null},{"id":"2308.03028","title":"Pre-Trained Large Language Models for Industrial Control","created":"2023-08-06","cited_by_count":16,"area":null},{"id":"2309.17207","title":"Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents","created":"2023-09-29","cited_by_count":16,"area":null},{"id":"2401.02814","title":"Object-Centric Instruction Augmentation for Robotic Manipulation","created":"2024-01-05","cited_by_count":16,"area":null},{"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":"2304.13269","title":"Games for Artificial Intelligence Research: A Review and Perspectives","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2306.12860","title":"Learning from Visual Observation via Offline Pretrained State-to-Go Transformer","created":"2023-06-22","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":"2502.05454","title":"Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following","created":"2025-02-08","cited_by_count":14,"area":null},{"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":"2210.01603","title":"Neural-Symbolic Recursive Machine for Systematic Generalization","created":"2022-10-04","cited_by_count":12,"area":null},{"id":"2511.20766","title":"OpenApps: Simulating Environment Variations to Measure UI-Agent Reliability","created":"2025-11-25","cited_by_count":12,"area":null},{"id":"2406.13264","title":"WONDERBREAD: A Benchmark for Evaluating Multimodal Foundation Models on Business Process Management Tasks","created":"2024-06-19","cited_by_count":11,"area":null},{"id":"2310.08549","title":"Cross-Episodic Curriculum for Transformer Agents","created":"2023-10-12","cited_by_count":10,"area":null},{"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":"2407.14872","title":"Adapt2Reward: Adapting Video-Language Models to Generalizable Robotic Rewards via Failure Prompts","created":"2024-07-20","cited_by_count":10,"area":null},{"id":"2502.15214","title":"The Evolving Landscape of LLM- and VLM-Integrated Reinforcement Learning","created":"2025-02-21","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":"2302.05614","title":"Cross-domain Random Pre-training with Prototypes for Reinforcement Learning","created":"2023-02-11","cited_by_count":9,"area":null},{"id":"2312.01097","title":"Planning as In-Painting: A Diffusion-Based Embodied Task Planning Framework for Environments under Uncertainty","created":"2023-12-02","cited_by_count":9,"area":null},{"id":"2403.19913","title":"MANGO: A Benchmark for Evaluating Mapping and Navigation Abilities of Large Language Models","created":"2024-03-29","cited_by_count":9,"area":null},{"id":"2407.18178","title":"PianoMime: Learning a Generalist, Dexterous Piano Player from Internet Demonstrations","created":"2024-07-25","cited_by_count":9,"area":null},{"id":"2409.01806","title":"LASP: Surveying the State-of-the-Art in Large Language Model-Assisted AI Planning","created":"2024-09-03","cited_by_count":9,"area":null},{"id":"2212.12669","title":"On Realization of Intelligent Decision-Making in the Real World: A Foundation Decision Model Perspective","created":"2022-12-24","cited_by_count":8,"area":null},{"id":"2301.12066","title":"Truth Machines: Synthesizing Veracity in AI Language Models","created":"2023-01-28","cited_by_count":8,"area":null},{"id":"2311.02018","title":"Active Reasoning in an Open-World Environment","created":"2023-11-03","cited_by_count":8,"area":null},{"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":"2304.00046","title":"Accelerating exploration and representation learning with offline pre-training","created":"2023-03-31","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}],"next_cursor":"100"}