FoldingAgent: Inferring Parametric Origami Procedures from Demonstration Videos

  • 类型：arxiv
  • 标识：2609.00377
  • 链接：https://arxiv.org/abs/2609.00377
  • 主分类：agent
  • 形态：method
  • 被引：0
  • 被引来源：Semantic Scholar + OpenAlex
  • S2被引：0
  • OpenAlex被引：0
  • 影响力被引：0
  • TLDR：FoldingAgent is presented, an agentic framework for inferring explicit parametric folding programs directly from origami demonstration videos that leverages the reasoning power of a pre-trained Vision-Language Model 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.
  • OpenAlex ID：W7206214643
  • OpenAlex DOI：10.48550/arxiv.2609.00377
  • DOI：10.48550/arxiv.2609.00377
  • DOI来源：OpenAlex
  • 开放获取：green
  • 开放获取链接：https://arxiv.org/pdf/2609.00377
  • OpenAlex更新：2026-09-06
  • 副分类：multimodal
  • 待LLM分类：否
  • 标题中文：FoldingAgent：从演示视频中推断参数化折纸过程
  • TLDR中文：本文提出 FoldingAgent，一个从折纸演示视频中推断显式参数化折纸程序的 Agent 框架，利用预训练 Vision-Language Model 的推理能力，并配备可模拟几何变换、验证物理合理性、检索与比较视觉内容以及评估自身预测的专用工具集。
  • 来源文件：
  • /inbox/tom/_candidates/2026-09-03-agent-rag-longcontext-candidates.json
  • [OpenAlex backfill]
  • [S2 enrich]