Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Virtual Community: An Open World for Humans, Robots, and Society
Qinhong Zhou, Hongxin Zhang, Xiangye Lin, Zheyuan Zhang, Yutian Chen, Wenjun Liu, Zunzhe Zhang, Sunli Chen, Lixing Fang, Qiushi Lyu, Xinyu Sun, Jincheng Yang and 7 more
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add explicit distance modeling (ablation) | MCTS Planner · Community Planning, 1-assistant | avg SR (%): 29.0 -> 42.4 | Improved |
| add explicit distance modeling (ablation) | LLM Planner · Community Planning, 1-assistant | avg SR (%): 44.4 -> 47.2 | Improved |
| add explicit distance modeling (ablation) | LLM Planner · Community Planning, 2-assistant | avg SR (%): 52.3 -> 50.6 | Hurt |
| use LLM planner instead of heuristic planner | planning · Search task, 2-assistant | SR (%): 51.4 -> 77.8 | Improved |
| use LLM planner instead of heuristic planner | planning · Carry task, 1-assistant | SR (%): 34.7 -> 29.9 | Hurt |
| add a second assistant | Heuristic planner · Community Planning | avg SR (%): 42.1 -> 54.6 | Improved |
| add a second assistant | MCTS Planner · Community Planning | avg SR (%): 42.4 -> 44.9 | Improved |
| upgrade dialogue backbone from GPT-4o to o1 (ablation) | main agent · Community Influence | win rate: 0.57 -> 0.60 | Improved |
| upgrade target-selection backbone from GPT-4o to o1 (ablation) | main agent · Community Influence | win rate: 0.57 -> 0.58 | Improved |
| upgrade target-selection backbone to o1 with GPT-4o dialogue (ablation) | main agent · Community Influence | conversion rate: 0.17 -> 0.06 | Hurt |
| add oracle grasp | Heuristic · Community Robot Challenge | avg SR (%): 19.9 -> 36.8 | Improved |
| decompose RL into separate reach and place policies (ablation) | RL w/ oracle grasp · Community Robot Challenge | avg SR (%): 31.0 -> 33.3 | Improved |
Closest papers by meaning
- Habitat 3.0: A Co-Habitat for Humans, Avatars, and Robots (ICLR 2024 · similarity 0.90)
- Human-Centric Open-Future Task Discovery: Formulation, Benchmark, and Scalable Tree-Based Search (AAAI 2026 · similarity 0.87)
- VirtualEnv: A Platform for Embodied AI Research (AAAI 2026 · similarity 0.87)
- LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents (NeurIPS 2025 · similarity 0.87)
- Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds (ICLR 2024 · similarity 0.87)
- Position: Evolving AI Collectives Enhance Human Diversity and Enable Self-Regulation (ICML 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
