Search-to-World：从用户请求经网络搜索到3D世界交付的评估
Search-to-World: Evaluation of 3D World Delivery from User Request through Web Search
浏览论文内容
中文总结 AI 辅助
提出Search-to-World评估任务及WorldSearcher框架，通过检索或重建实现3D世界交付，验证了相关观测不等于成功交付，联合训练恢复智能体可提升交付性能。
中文摘要 AI 辅助
智能体系统能够解释用户请求、搜索实时网络并使用外部工具，但其将检索到的网络内容转化为可用3D世界的能力尚未得到系统评估。目前不存在针对该能力的既定端到端流程或基准。我们提出Search-to-World，一个涵盖请求理解、网络视觉内容检索和3D世界交付的端到端评估任务。我们定义了观测检索率（ORR）和世界交付率（WDR），以区分观测到相关内容与成功交付符合请求且感知上可接受的世界。我们还提出了WorldSearcher，一个先复用后重建的框架，将现有搜索智能体连接到世界交付：它首先检索可复用的3D世界，当没有可用世界时，则从视频重建世界。一个结构化的恢复控制器在失败后修正时间定位、替换源视频或重新表述查询。利用WorldSearcher，我们在Search-to-World上对代表性模型进行基准测试，并研究针对恢复子代理的监督微调（SFT）。结果表明，交付依赖于底层智能体模型，且相关内容的观测并不能确保世界交付。联合训练恢复智能体提高了交付成功率和行动效率。Search-to-World使智能体3D世界交付变得可衡量，而WorldSearcher提供了一个具有恢复能力的实用评估框架。
英文摘要
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.
发表机构
- Institute of Artificial Intelligence, China Telecom (TeleAI)（中国电信人工智能研究院（TeleAI））
- Shanghai Jiao Tong University（上海交通大学）
- Shanghai Innovation Institution（上海创新研究院）
- ActiMind
- Nanjing University（南京大学）
- Fudan University（复旦大学）
机构由 AI 辅助整理，请以论文原文为准。
