{"list":"other","total":52,"rows":[{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"2402.01680","title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","created":"2024-01-21","cited_by_count":769},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2410.07864","title":"RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation","created":"2024-10-10","cited_by_count":691},{"id":"2308.10848","title":"AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors","created":"2023-08-21","cited_by_count":598},{"id":"2302.09419","title":"A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT","created":"2023-02-18","cited_by_count":368},{"id":"2307.01928","title":"Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners","created":"2023-07-04","cited_by_count":308},{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261},{"id":"2307.02485","title":"Building Cooperative Embodied Agents Modularly with Large Language Models","created":"2023-07-05","cited_by_count":237},{"id":"2312.07843","title":"Foundation Models in Robotics: Applications, Challenges, and the Future","created":"2023-12-13","cited_by_count":216},{"id":"2407.06886","title":"Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI","created":"2024-07-09","cited_by_count":179},{"id":"2307.04738","title":"RoCo: Dialectic Multi-Robot Collaboration with Large Language Models","created":"2023-07-10","cited_by_count":172},{"id":"2309.10062","title":"SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models","created":"2023-09-18","cited_by_count":153},{"id":"2403.12910","title":"Yell At Your Robot: Improving On-the-Fly from Language Corrections","created":"2024-03-19","cited_by_count":124},{"id":"2306.06531","title":"AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers","created":"2023-06-10","cited_by_count":113},{"id":"2309.15943","title":"Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?","created":"2023-09-27","cited_by_count":106},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103},{"id":"2403.12482","title":"Embodied LLM Agents Learn to Cooperate in Organized Teams","created":"2024-03-19","cited_by_count":82},{"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},{"id":"2405.11106","title":"LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions","created":"2024-05-17","cited_by_count":67},{"id":"2301.02555","title":"\"No, to the Right\" -- Online Language Corrections for Robotic Manipulation via Shared Autonomy","created":"2023-01-06","cited_by_count":60},{"id":"2402.15538","title":"AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System","created":"2024-02-23","cited_by_count":53},{"id":"2307.13929","title":"Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perception","created":"2023-07-26","cited_by_count":52},{"id":"2310.02071","title":"Towards End-to-End Embodied Decision Making via Multi-modal Large Language Model: Explorations with GPT4-Vision and Beyond","created":"2023-10-03","cited_by_count":51},{"id":"2310.20151","title":"Multi-Agent Consensus Seeking via Large Language Models","created":"2023-10-31","cited_by_count":50},{"id":"2312.15224","title":"LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination","created":"2023-12-23","cited_by_count":48},{"id":"2405.14314","title":"Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration","created":"2024-05-23","cited_by_count":45},{"id":"2409.15146","title":"COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language Models","created":"2024-09-23","cited_by_count":45},{"id":"2407.06089","title":"Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models","created":"2024-07-08","cited_by_count":44},{"id":"2311.13884","title":"Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approach","created":"2023-11-23","cited_by_count":38},{"id":"2409.20560","title":"LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Planner","created":"2024-09-30","cited_by_count":32},{"id":"2306.10376","title":"CLARA: Classifying and Disambiguating User Commands for Reliable Interactive Robotic Agents","created":"2023-06-17","cited_by_count":30},{"id":"2109.07872","title":"Knowledge-based Embodied Question Answering","created":"2021-09-16","cited_by_count":29},{"id":"2403.08282","title":"Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigation","created":"2024-03-13","cited_by_count":24},{"id":"2410.21040","title":"LiP-LLM: Integrating Linear Programming and dependency graph with Large Language Models for multi-robot task planning","created":"2024-10-28","cited_by_count":24},{"id":"2402.04578","title":"S-Agents: Self-organizing Agents in Open-ended Environments","created":"2024-02-07","cited_by_count":22},{"id":"2002.04235","title":"Learning Structured Communication for Multi-agent Reinforcement Learning","created":"2020-02-11","cited_by_count":21},{"id":"2202.00104","title":"Generalization in Cooperative Multi-Agent Systems","created":"2022-01-31","cited_by_count":19},{"id":"2403.11075","title":"GOMA: Proactive Embodied Cooperative Communication via Goal-Oriented Mental Alignment","created":"2024-03-17","cited_by_count":16},{"id":"2305.05909","title":"Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers","created":"2023-05-10","cited_by_count":15},{"id":"2209.03859","title":"A Survey on Large-Population Systems and Scalable Multi-Agent Reinforcement Learning","created":"2022-09-08","cited_by_count":14},{"id":"2411.04679","title":"CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-Agent Cooperation","created":"2024-11-07","cited_by_count":12},{"id":"2406.04086","title":"A Survey of Language-Based Communication in Robotics","created":"2024-06-06","cited_by_count":10},{"id":"2409.16030","title":"MHRC: Closed-loop Decentralized Multi-Heterogeneous Robot Collaboration with Large Language Models","created":"2024-09-24","cited_by_count":10},{"id":"2411.06736","title":"MrSteve: Instruction-Following Agents in Minecraft with What-Where-When Memory","created":"2024-11-11","cited_by_count":9},{"id":"2409.12274","title":"Hierarchical LLMs In-the-Loop Optimization for Real-Time Multi-Robot Target Tracking under Unknown Hazards","created":"2024-09-18","cited_by_count":8},{"id":"2307.13957","title":"Heterogeneous Embodied Multi-Agent Collaboration","created":"2023-07-26","cited_by_count":6},{"id":"2405.15777","title":"Multi-agent Collaborative Perception for Robotic Fleet: A Systematic Review","created":"2024-03-22","cited_by_count":2}],"next_cursor":null}