Scene2Demo: Self-Evolving Embodied Data Generation via Object-Action Graph

2026-02-12 · Xiang Liu, Sen Cui, Guocai Yao, Zhong Cao, Jingheng Ma, Min Zhang, Changshui Zhang arxiv

We present Scene2Demo, a self-evolving framework for offline embodied data generation. Given a single real-world RGB image and a user query, Scene2Demo constructs an interactive simulated scene and generates executable task configurations, multi-view execution videos, and offline robot-learning datasets. Scene2Demo uses a structured multi-module workflow via an object-action graph, representing task generation through object-centric configurations and action transitions. Failed or incomplete executions are further refined by feedback agents that inspect visual rollouts and revise action flows through sequence modification or parameter adjustment. Across 102 automatically generated primitive scene-task pairs, Scene2Demo achieves a 71.6\% execution success rate; on four representative long-horizon tasks, self-evolution improves both task success and subtask-level execution quality over primitive-only execution, and comparisons with RoboGen and GenSim2 show stronger task planning and execution performance under automated data-generation settings. Finally, behavior cloning policies achieve 96.0\% and 92.0\% success on two representative tasks, validating that the generated data can support downstream policy learning. Our project page is available at https://scene2demo-anon.github.io/ .

📄 PDF Abstract BibTeX arXiv:2602.12065

Code (0)

등록된 구현이 없습니다.

Self-evolving Embodied AI

2026-02-04 · Tongtong Feng, Xin Wang, Wenwu Zhu arxiv

Embodied Artificial Intelligence (AI) is an intelligent system formed by agents and their environment through active perception, embodied cognition, and action interaction. Existing embodied AI remains confined to human-…

SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning

2026-05-10 · Haoqiang Kang, Xiaokang Ye, Yuhan Liu, Siddhant Hitesh Mantri 외 arxiv

LLM/VLM-based digital agents have advanced rapidly thanks to scalable sandboxes for coding, web navigation, and computer use, which provide rich interactive training grounds. In contrast, embodied agents still lack abund…

3D Generation

Self-Evolving Cognitive Framework via Causal World Modeling for Embodied Scientific Intelligence

2026-06-21 · Yi Yu, Tetsunari Inamura arxiv

Current embodied world models are primarily optimized for predictive objectives, limiting their ability to generalize under distribution shifts and reason systematically about unseen situations and hypothetical intervent…

Self-Evolving Embodied Agents via Skill-Harness Evolution

2026-08-11 · Peidong Wang, Zhiming Ma, Ying Chang, Xufang Luo 외 hf

Embodied agents are increasingly built as systems around foundation models, where performance depends not only on model weights but also on the skills, context, action interfaces, and execution harness surrounding the mo…

Reinforcement Learning

EvoMemNav: Efficient Self-Evolving Fine-Grained Memory for Zero-Shot Embodied Navigation

2026-06-02 · Zuhao Ge, Xiaosong Jia, Chao Wu, Yuchen Zhou 외 arxiv

Building memory is essential for long-horizon planning in zero-shot embodied navigation. Detector-centric scene graphs often compress observations into sparse nodes, discarding fine-grained visual evidence and accumulati…

Zero-shot Generalization 3D Reconstruction