mlsanityData to 14 Oct 2026

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

arXiv 2601.16984 ↗First posted 17 Nov 2025cs.LG cs.AI cs.CLcited by 0

On the map: Retrieval-augmented generation → Agentic RAG, agents and memory

also in 1 more
Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation. Builds on 20 of its 31 references that are in the map. First posted on arXiv 17 Nov 2025.

Builds on

20 of 31 references.

References · 20

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  3. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  4. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 318
  5. 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 235
  6. 2023Take a Step Back: Evoking Reasoning via Abstraction in Large Language Modelscited by 159
  7. 2023Lift Yourself Up: Retrieval-augmented Text Generation with Self Memorycited by 103
  8. 2024Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunitiescited by 83
  9. 2023UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluationcited by 75
  10. 2023KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Basescited by 52
  11. 2024TSpec-LLM: An Open-source Dataset for LLM Understanding of 3GPP Specificationscited by 27
  12. 2024Telco-RAG: Navigating the Challenges of Retrieval-Augmented Language Models for Telecommunicationscited by 26
8 more
  1. 2024Automated Evaluation of Retrieval-Augmented Language Models with Task-Specific Exam Generationcited by 25
  2. 2024Tele-LLMs: A Series of Specialized Large Language Models for Telecommunicationscited by 25
  3. 2024Evaluation of RAG Metrics for Question Answering in the Telecom Domaincited by 20
  4. 2024Query Routing for Homogeneous Tools: An Instantiation in the RAG Scenariocited by 10
  5. 2023Artificial Intelligence in 3GPP 5G-Advanced: A Surveycited by 8
  6. 2024Leveraging Fine-Tuned Retrieval-Augmented Generation with Long-Context Support: For 3GPP Standardscited by 8
  7. 2025Chat3GPP: An Open-Source Retrieval-Augmented Generation Framework for 3GPP Documentscited by 5
  8. 2024Telco-DPR: A Hybrid Dataset for Evaluating Retrieval Models of 3GPP Technical Specificationscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024TeleOracle: Fine-Tuned Retrieval-Augmented Generation with Long-Context Support for Network
  2. 2025Telco-oRAG: Optimizing Retrieval-augmented Generation for Telecom Queries via Hybrid Retrieval and Neural Routing
  3. 2026MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains
  4. 2025Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges
  5. 2026VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents
  6. 2025HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation
  7. 2025RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval Augmented Generation Systems
  8. 2026Telco-GAIA: Bilingual Benchmark for Agents in Telecom Domain