评估用户请求通过网络搜索生成3D世界的能力，提出新评测框架与可恢复生成系统。
Search-to-World: Evaluation of 3D World Delivery from User Request through Web Search
- 构建端到端流程：从理解请求、检索网页视觉内容到生成3D世界。
- 提出ORR与WDR指标，发现相关内容获取不等于成功交付3D世界。
- 引入可恢复生成框架WorldSearcher，支持重用或视频重构，提升交付成功率。
智能体系统能解析用户请求、检索实时网络内容并使用外部工具，但其将检索到的网络内容转化为可用3D世界的能力尚未被系统评估。目前缺乏端到端流程与基准测试。本文提出Search-to-World任务，涵盖请求理解、网络视觉内容检索与3D世界生成全过程。定义观测检索率（ORR）与世界交付率（WDR），以区分观察到相关内容与成功交付符合请求、感知可接受的3D世界之间的差异。提出WorldSearcher系统，采用‘复用-重构’范式：先检索可复用的3D世界，若无则基于视频重建；结构化恢复控制器在失败后修正时间定位、替换源视频或重写查询。利用WorldSearcher对代表性模型进行评测，并研究恢复子代理的监督微调（SFT）。结果表明，交付能力取决于底层智能体性能，且相关内容观测不保证世界交付。联合训练恢复代理可提升交付成功率与动作效率。Search-to-World使智能体3D世界生成能力可度量，WorldSearcher则提供具备恢复能力的实际评估工具。
原文摘要 · Abstract (English)
Agentic systems can interpret user requests, search the live web, and use external tools, but their ability to transform retrieved web content into a usable 3D world has not been systematically evaluated. No established end-to-end pipeline or benchmark exists for this capability. We introduce Search-to-World, an end-to-end evaluation task covering request understanding, web visual-content retrieval, and 3D-world delivery. We define Observed Retrieval Rate (ORR) and World Delivery Rate (WDR) to distinguish observing relevant content from successfully delivering a request-aligned, perceptually acceptable world. We also present WorldSearcher, a reuse-then-reconstruction harness that connects existing search agents to world delivery: it first retrieves reusable 3D worlds and, when none are available, reconstructs a world from video. A structured recovery controller revises temporal grounding, replaces source videos, or reformulates queries after failure. Using WorldSearcher, we benchmark representative models on Search-to-World and study supervised fine-tuning (SFT) for recovery subagents. Results show that delivery depends on the underlying agentic model, and that relevant-content observation does not ensure world delivery. Jointly training recovery agents improves delivery success and action efficiency. Search-to-World makes agentic 3D-world delivery measurable, while WorldSearcher provides a practical evaluation harness with recovery capabilities.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。