Metraipolis › archive › dc_64709c08ac8b
TelecomGPT-R1: A Unified Open-Source Reasoner for the Telecom Stack — arXiv:2608.26126
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.26126
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T15:18:11.757Z
- SHA-256 of the archived text
5f022edba95d0c19305ed01c6454e3dfb10b05ae624de5fe7eba245c77f3afe6- Stable URL of this page
https://metraipolis.com/documento/dc_64709c08ac8b
How to cite
TelecomGPT-R1: A Unified Open-Source Reasoner for the Telecom Stack — arXiv:2608.26126 — arXiv (en), https://arxiv.org/abs/2608.26126 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_64709c08ac8b (Metraipolis archive dc_64709c08ac8b, sha256 5f022edba95d0c19305ed01c6454e3dfb10b05ae624de5fe7eba245c77f3afe6)
BibTeX
@misc{dc64709c08ac8b,
title = {TelecomGPT-R1: A Unified Open-Source Reasoner for the Telecom Stack — arXiv:2608.26126},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.26126},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_64709c08ac8b; sha256 5f022edba95d0c19305ed01c6454e3dfb10b05ae624de5fe7eba245c77f3afe6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26126. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Telecommunications is a high-leverage domain for large language model (LLM)-based reasoning because routine engineering workflows require joint grounding in normative specifications, operational telemetry, vendor-specific fault evidence, and exact RF/network calculations. However, current LLM integration in telecom remains bottlenecked by a two-sided capability gap: generic reasoners often lack telecom-specific grounding, while domain-specific telecom LLMs remain limited in structured, multi-step reasoning. To bridge this gap, we release TelecomGPT-R1-9B, a unified open-source telecom reasoner that ranks top-performing on the GSMA open telco leaderboard. Specifically, we curate a 67,427-example supervised fine-tuning (SFT) corpus organized around four complementary reasoning axes: protocol, knowledge, modeling, and fault. The corpus is built from axis-matched public web sources and enhanced through axis-specific chain-of-thought (CoT) generation and prefix-continuation self-validation. Starting from Qwen3.5-9B, we further develop a two-stage post-training recipe. First, multi-teacher low-rank adaptation (LoRA)-based SFT injects telecom knowledge and induces axis-specific reasoning formats. Second, group relative policy optimization (GRPO), stabilized by decoupled clip and dynamic sampling policy optimization (DAPO), optimizes the policy using four axis-aligned binary verifier rewards. Across seven public telecom benchmarks, TelecomGPT-R1-9B ranks first among open-source telecom LLMs and achieves a seven-axis mean comparable to state-of-the-art closed-source frontier reasoners. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Information Theory (cs.IT). Pagina del lavoro: https://arxiv.org/abs/2608.26126 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T15:15:18.021Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).