TelcoAI: Advancing 3GPP Technical Specification Search through Agentic Multi-Modal Retrieval-Augmented Generation

TL;DR

TelcoAI is a novel multi-modal retrieval-augmented generation system that significantly improves understanding and querying of complex 3GPP telecommunications specifications by integrating structured, multi-modal, and agentic reasoning techniques.

Contribution

The paper introduces TelcoAI, a new system that combines section-aware chunking, structured query planning, and multi-modal fusion to enhance technical document comprehension and retrieval.

Findings

Achieves 87% recall in document retrieval

Reaches 83% claim recall in expert-curated queries

Attains 92% faithfulness, 16% better than baselines

Abstract

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.