Virtual Community: An Open World for Humans, Robots, and Society
Not on the map. Why?
Abstract (arXiv)
The rapid progress in AI and Robotics may lead to a profound societal transformation, as humans and robots begin to coexist within shared communities, introducing both opportunities and challenges. To explore this future, we present Virtual Community-an open-world platform for humans, robots, and society-built on a universal physics engine and grounded in real-world 3D scenes. With Virtual Community, we aim to enable the study of embodied social intelligence at scale. To support these, Virtual Community features: 1) An open-source multi-agent physics simulator that supports robots, humans, and their interactions within a society; 2) A large-scale, real-world aligned community generation pipeline, including vast outdoor space, diverse indoor scenes, and a community of grounded agents with rich characters and appearances. Leveraging Virtual Community, we propose two novel challenges. The Community Planning Challenge evaluates multi-agent reasoning and planning ability in open-world settings, such as cooperating to help agents with daily activities and efficiently connecting other agents. The Community Robot Challenge requires multiple heterogeneous robots to collaborate in solving complex open-world tasks. We evaluate various baselines on these tasks and demonstrate the challenges in both high-level open-world task planning and low-level cooperation controls. We hope that Virtual Community will unlock further study of human-robot coexistence within open-world environments.
Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 75 of its 91 references that are in the map. First posted on arXiv 20 Aug 2025.
Builds on
75 of 91 references.
References · 75
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2023GPT-4 Technical Reportcited by 18,396
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2024The Llama 3 Herd of Modelscited by 14,715
- 2023Visual Instruction Tuningcited by 7,869
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
- 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
- 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
- 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
- 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
- 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
38 more
- 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
- 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
- 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
- 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,476
- 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
- 2018Demystifying MMD GANscited by 1,293
- 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
- 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,027
- 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
- 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
- 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 929
- 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 869
- 2019The StarCraft Multi-Agent Challengecited by 597
- 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 595
- 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 560
- 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 462
- 2023Cognitive Architectures for Language Agentscited by 429
- 2018VirtualHome: Simulating Household Activities via Programscited by 415
- 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 398
- 20203D-FRONT: 3D Furnished Rooms with layOuts and semaNTicscited by 380
- 2022ProcTHOR: Large-Scale Embodied AI Using Procedural Generationcited by 380
- 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 349
- 2023LayoutGPT: Compositional Visual Planning and Generation with Large Language Modelscited by 347
- 2018Learning to Drive in a Daycited by 273
- 2023Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Modelscited by 269
- 2023Holodeck: Language Guided Generation of 3D Embodied AI Environmentscited by 268
- 2020ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulationcited by 250
- 2023Building Cooperative Embodied Agents Modularly with Large Language Modelscited by 237
- 2024ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AIcited by 229
- 2023Habitat 3.0: A Co-Habitat for Humans, Avatars and Robotscited by 228
- 2023RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulationcited by 218
- 2021Fake It Till You Make It: Face analysis in the wild using synthetic data alonecited by 200
- 2021ATISS: Autoregressive Transformers for Indoor Scene Synthesiscited by 200
- 2021iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Taskscited by 194
- 2020RoboTHOR: An Open Simulation-to-Real Embodied AI Platformcited by 193
- 2023Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Researchcited by 160
- 2020iGibson 1.0: a Simulation Environment for Interactive Tasks in Large Realistic Scenescited by 155
- 2022Multi-Agent Reinforcement Learning is a Sequence Modeling Problemcited by 155
50 most cited of 75 All 75 (JSON)
Built on by
Citing papers per year: 2025: 6; 2026: 7.
13 papers.
Sort:
By area:
- 2025SimWorld: An Open-ended Realistic Simulator for Autonomous Agents in Physical and Social Worldscited by 12
- 2026Articulation in Motion: Prior-free Part Mobility Analysis for Articulated Objects By Dynamic-Static Disentanglementcited by 6
- 2025TongSIM: A General Platform for Simulating Intelligent Machinescited by 4
- 2025UrbanWorld2.0: A Multimodal Agentic Framework for Reality-Aligned 3D World Generation at City-Scalecited by 3
- 2026AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agentscited by 3
- 2025Evaluating Multimodal Large Language Models with Daily Composite Tasks in Home Environmentscited by 1
- 2025FreeAskWorld: An Interactive and Closed-Loop Simulator for Human-Centric Embodied AIcited by 1
- 2026UrbanGround: From Local Perception to Spatial Agency in a Real-Scale Citycited by 1
- 2025S3IT: A Benchmark for Spatially Situated Social Intelligence Testcited by 0
- 2026Sentinel: Embodied Cooperative Spatial Reasoning and Planningcited by 0
- 2026NavVerse: Benchmarking Indoor-to-Outdoor Embodied Navigation in Continuous Robot Simulationcited by 0
- 2026SIMLIFE: Pattern Understanding for Long-Horizon Human-Agent Partnershipcited by 0
1 more
- 2026Generative Embodied Multiple Behavior Control Systems for Human-like Agents19 Sep 2026
- 2026SIMLIFE: Pattern Understanding for Long-Horizon Human-Agent Partnership17 Sep 2026
- 2026UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City27 Aug 2026
- 2026NavVerse: Benchmarking Indoor-to-Outdoor Embodied Navigation in Continuous Robot Simulation22 Jul 2026
- 2026AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents29 May 2026
- 2026Sentinel: Embodied Cooperative Spatial Reasoning and Planning25 May 2026
- 2026Articulation in Motion: Prior-free Part Mobility Analysis for Articulated Objects By Dynamic-Static Disentanglement3 Mar 2026
- 2025TongSIM: A General Platform for Simulating Intelligent Machines23 Dec 2025
- 2025S3IT: A Benchmark for Spatially Situated Social Intelligence Test23 Dec 2025
- 2025SimWorld: An Open-ended Realistic Simulator for Autonomous Agents in Physical and Social Worlds30 Nov 2025
- 2025UrbanWorld2.0: A Multimodal Agentic Framework for Reality-Aligned 3D World Generation at City-Scale22 Nov 2025
- 2025FreeAskWorld: An Interactive and Closed-Loop Simulator for Human-Centric Embodied AI17 Nov 2025
- 2026Articulation in Motion: Prior-free Part Mobility Analysis for Articulated Objects By Dynamic-Static Disentanglementcited by 6
- 2025UrbanWorld2.0: A Multimodal Agentic Framework for Reality-Aligned 3D World Generation at City-Scalecited by 3
- 2026AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agentscited by 3
- 2025FreeAskWorld: An Interactive and Closed-Loop Simulator for Human-Centric Embodied AIcited by 1
- 2025S3IT: A Benchmark for Spatially Situated Social Intelligence Testcited by 0
- 2026NavVerse: Benchmarking Indoor-to-Outdoor Embodied Navigation in Continuous Robot Simulationcited by 0
- 2026SIMLIFE: Pattern Understanding for Long-Horizon Human-Agent Partnershipcited by 0
- 2026Generative Embodied Multiple Behavior Control Systems for Human-like Agentscited by 0
- 2026Generative Embodied Multiple Behavior Control Systems for Human-like Agents19 Sep 2026
- 2026SIMLIFE: Pattern Understanding for Long-Horizon Human-Agent Partnership17 Sep 2026
- 2026NavVerse: Benchmarking Indoor-to-Outdoor Embodied Navigation in Continuous Robot Simulation22 Jul 2026
- 2026AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents29 May 2026
- 2026Articulation in Motion: Prior-free Part Mobility Analysis for Articulated Objects By Dynamic-Static Disentanglement3 Mar 2026
- 2025S3IT: A Benchmark for Spatially Situated Social Intelligence Test23 Dec 2025
- 2025UrbanWorld2.0: A Multimodal Agentic Framework for Reality-Aligned 3D World Generation at City-Scale22 Nov 2025
- 2025FreeAskWorld: An Interactive and Closed-Loop Simulator for Human-Centric Embodied AI17 Nov 2025