用智能代理+多模态技术提升电信标准文档的精准检索与生成。
TelcoAI: Advancing 3GPP Technical Specification Search through Agentic Multi-Modal Retrieval-Augmented Generation
- 构建智能代理系统，分步解析复杂查询并融合文本与图表信息。
- 在专家标注测试中实现87%召回率、92%忠实度，较现有方法提升16%。
- 适合电信研发人员快速定位3GPP标准中的技术细节和跨文档关联。
第三代合作伙伴计划（3GPP）制定的复杂技术规范对全球通信至关重要，但其层级结构、密集格式和多模态内容使其难以处理。尽管大语言模型（LLMs）展现潜力，现有方法在应对复杂查询、视觉信息和文档依赖关系方面仍显不足。我们提出TelcoAI，一种专为3GPP文档设计的智能代理式多模态检索增强生成系统。该系统引入章节感知切块、结构化查询规划、元数据引导检索及文本与图表的多模态融合。在多个基准测试（包括专家标注查询）上，系统达到87%的召回率、83%的主张召回率和92%的忠实度，相较最先进基线提升16%。结果表明，智能代理与多模态推理在技术文档理解中的有效性，推动了真实电信科研与工程场景的实用解决方案。
原文摘要 · Abstract (English)
The 3rd Generation Partnership Project (3GPP) produces complex technical specifications essential to global telecommunications, yet their hierarchical structure, dense formatting, and multi-modal content make them difficult to process. While Large Language Models (LLMs) show promise, existing approaches fall short in handling complex queries, visual information, and document interdependencies. We present TelcoAI, an agentic, multi-modal Retrieval-Augmented Generation (RAG) system tailored for 3GPP documentation. TelcoAI introduces section-aware chunking, structured query planning, metadata-guided retrieval, and multi-modal fusion of text and diagrams. Evaluated on multiple benchmarks-including expert-curated queries-our system achieves $87\%$ recall, $83\%$ claim recall, and $92\%$ faithfulness, representing a $16\%$ improvement over state-of-the-art baselines. These results demonstrate the effectiveness of agentic and multi-modal reasoning in technical document understanding, advancing practical solutions for real-world telecommunications research and engineering.
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。