Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.16984 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914276674895872 |
|---|---|
| author | Ghosh, Rahul Liu, Chun-Hao Rele, Gaurav Ravipati, Vidya Sagar Aouad, Hazar |
| author_facet | Ghosh, Rahul Liu, Chun-Hao Rele, Gaurav Ravipati, Vidya Sagar Aouad, Hazar |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_16984 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TelcoAI: Advancing 3GPP Technical Specification Search through Agentic Multi-Modal Retrieval-Augmented Generation Ghosh, Rahul Liu, Chun-Hao Rele, Gaurav Ravipati, Vidya Sagar Aouad, Hazar Machine Learning Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Information Retrieval Multimedia 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. |
| title | TelcoAI: Advancing 3GPP Technical Specification Search through Agentic Multi-Modal Retrieval-Augmented Generation |
| topic | Machine Learning Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Information Retrieval Multimedia |
| url | https://arxiv.org/abs/2601.16984 |