analiza aiqbench
FoldingAgent represents a significant advancement in embodied AI by bridging the gap between unstructured visual demonstrations of origami and executable parametric folding programs. By leveraging Vision-Language Models equipped with physical simulation tools, this framework effectively mitigates compounding errors inherent in multi-step sequential tasks without relying on pre-defined crease patterns. This work highlights the growing capability of agentic systems to translate human intuition into precise computational geometry for complex manipulation tasks.
FoldingAgent: Inferring Parametric Origami Procedures from Demonstration Videos
arXiv:2609.00377v1 Announce Type: cross Abstract: We present FoldingAgent, an agentic framework for inferring explicit parametric folding programs directly from origami demonstration videos. Our framework leverages the reasoning power of a pre-trained Vision-Language Model (VLM) equipped with a suite of specialized tools that enable the agent to simulate geometric transitions, verify physical plausibility, retrieve and compare visual content, and evaluate its own predictions. To translate visual content into folding programs, we define a parametric space that consists of the paper's geometry and a set of parametric folding actions. Unlike models that predict static crease patterns, our agent operates sequentially and possesses the ability to re-plan its actions, effectively mitigating the compounding errors inherent in multi-step folding. Our approach takes a step toward closing the gap between human origami knowledge, which is primarily shared through unstructured visual demonstrations, and computational methods, which typically rely on structured, parametric representations such as a crease pattern or an executable parametric plan. We evaluate our approach on PurelandFold, a newly curated benchmark of diverse Pureland origami videos with ground-truth geometry and action labels. Our results demonstrate that by combining VLM reasoning with a set of specialized tools and physical simulation, we can successfully transform unstructured visual demonstrations into executable, physically plausible folding procedures.
Abstract:We present FoldingAgent, an agentic framework for inferring explicit parametric folding programs directly from origami demonstration videos. Our framework leverages the reasoning power of a pre-trained Vision-Language Model (VLM) equipped with a suite of specialized tools that enable the agent to simulate geometric transitions, verify physical plausibility, retrieve and compare visual content, and evaluate its own predictions. To translate visual content into folding programs, we define a parametric space that consists of the paper's geometry and a set of parametric folding actions. Unlike models that predict static crease patterns, our agent operates sequentially and possesses the ability to re-plan its actions, effectively mitigating the compounding errors inherent in multi-step folding. Our approach takes a step toward closing the gap between human origami knowledge, which is primarily shared through unstructured visual demonstrations, and computational methods, which typically rely on structured, parametric representations such as a crease pattern or an executable parametric plan. We evaluate our approach on PurelandFold, a newly curated benchmark of diverse Pureland origami videos with ground-truth geometry and action labels. Our results demonstrate that by combining VLM reasoning with a set of specialized tools and physical simulation, we can successfully transform unstructured visual demonstrations into executable, physically plausible folding procedures.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Graphics (cs.GR)
arXiv:2609.00377 [cs.CV]
(or arXiv:2609.00377v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2609.00377 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 304 cuvinte
Subiecte conexe
Developing Healthcare Robotics with GPU-Native Medical Physics Simulation
NVIDIA · 28 iul. 2026
Robots Acquire Manipulation Skills in Seconds from a Single Human Video
arXiv · 23 iul. 2026
OpenWAM: An Open Framework for Composable World-Action Models
arXiv · 7 oct. 2026
$R^2$-WAM: Repair-and-Reject Post-Training for World Action Models
arXiv · 6 oct. 2026