arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.00030cs.LG
收藏

RAPTOR-AI用于灾难OODA循环:基于经验驱动的多模态RAG框架

RAPTOR-AI for Disaster OODA Loop: Hierarchical Multimodal RAG with Experience-Driven Agentic Decision-Making

Takato Yasuno

AI总结:

RAPTOR-AI通过分层多模态RAG框架,结合经验驱动的代理控制和LoRA适应,提升灾害响应中的检索精度、情境基础性和任务分解准确性。

摘要:

人道主义援助与灾害救援(HADR)行动需要快速整合多模态信息以在极端不确定性下做出时间敏感的决策。传统信息系统难以处理灾难数据的碎片化和多模态性质,并缺乏动态紧急情境中必需的自适应推理能力。本文介绍了RAPTOR-AI,一种基于经验驱动的多模态检索增强生成(RAG)框架,通过实现动态、经验驱动的决策支持来超越传统静态知识库。该系统通过三个关键创新解决HADR需求:从多种来源构建分层多模态知识(文本报告、航拍图像、历史文献)、基于情境的熵感知代理控制,动态选择最优检索策略,以及使用LoRA适应进行经验知识整合。该框架利用BLIP图像理解、ColVBERT嵌入和长上下文摘要在OODA循环(观察、定向、决定、行动)战术框架中构建分层知识树。实验显示,与现有方法相比,检索精度提高了23%,情境基础性提高了31%,任务分解准确性提高了27%,并且能够高效扩展到3000个文档块。

英文摘要:

Humanitarian Assistance and Disaster Relief (HADR) operations demand rapid synthesis of multimodal information for time-critical decision-making under extreme uncertainty. Traditional information systems struggle with the fragmented, multimodal nature of disaster data and lack adaptive reasoning capabilities essential for dynamic emergency contexts. This work introduces RAPTOR-AI, an agentic multimodal Retrieval-Augmented Generation (RAG) framework that advances beyond conventional static knowledge bases by implementing dynamic, experience-driven decision support for disaster response. The system addresses HADR requirements across initial rescue, recovery, and reconstruction phases through three key innovations: hierarchical multimodal knowledge construction from diverse sources (textual reports, aerial imagery, historical documentation), entropy-aware agentic control that dynamically selects optimal retrieval strategies based on situational context, and experiential knowledge integration using LoRA adaptation for both expert and non-expert responders. The framework constructs hierarchical knowledge trees from 46 tsunami-related PDFs (2,378 pages) using BLIP-based image understanding, ColVBERT embeddings, and long-context summarization within the OODA loop (Observe, Orient, Decide, Act) tactical framework. Experiments demonstrate significant improvements over existing approaches: 23\% improvement in retrieval precision, 31\% better situational grounding, and 27\% enhanced task decomposition accuracy, with efficient scaling up to 3,000 document chunks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑