Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Toward Embodied World Agents via Embodied-Planning Dataset and Interactive World Models
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes an embodied-planning dataset and interactive world models toward general embodied world agents operating across diverse 3D worlds.
Problem
Most embodied agents are confined to specific tasks in a single scene and transfer poorly to new environments; general embodied agents for open-world settings remain under-explored.
Approach
Combines an embodied-planning dataset with interactive world models to build agents that perceive, reason, and act across diverse 3D worlds. Details beyond the abstract are not available.
Closest papers by meaning
- Learning 3D Persistent Embodied World Models (NeurIPS 2025 · similarity 0.92)
- An Embodied Generalist Agent in 3D World (ICML 2024 · similarity 0.90)
- SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning (NeurIPS 2026 · similarity 0.90)
- WorldSimBench: Towards Video Generation Models as World Simulators (ICML 2025 · similarity 0.90)
- COMBO: Compositional World Models for Embodied Multi-Agent Cooperation (ICLR 2025 · similarity 0.89)
- 3D-VLA: A 3D Vision-Language-Action Generative World Model (ICML 2024 · similarity 0.89)
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.