The new AI Telco troubleshooting competition invites telcos and researchers to build LLMs for root cause analysis of network faults.
Global organisation GSMA, in collaboration with ETSI, IEEE GenAINet, ITU, and TM Forum, has launched The AI Telco Troubleshooting Challenge, a new global competition aimed at transforming the way telecom operators diagnose and resolve network faults.
The initiative invites telecom operators, AI researchers, and startups to develop large language models capable of performing root cause analysis (RCA) on complex network incidents, one of the sector’s most persistent and costly challenges.
Participants will submit models across several categories. The Generalisation to New Faults track will assess LLMs that can identify causes of unfamiliar issues; the Small Models at the Edge category will focus on lightweight, edge-deployable models suited to on-site environments; and the Explainability & Reasoning category will evaluate AI systems that can clearly articulate their logic.
Entries will be judged on accuracy, efficiency, reasoning capability, and security considerations. The challenge is supported by headline partners Huawei, InterDigital, NextGCloud, RelationalAI, and xFlowResearch, with technical advisors from AT&T providing further guidance.
Dario Sabella, Chair of ETSI MEC, said: “This challenge addresses some of the most pressing research questions in our industry, such as model generalisation and the efficiency of edge-based AI. By providing unparalleled access to specialised data and resources, we are accelerating the adoption of Telco AI.”
Professor Merouane Debbah, General Chair of IEEE GenAINet ETI, added: “Through this challenge, we are tackling core research and engineering challenges, such as generalisation to unseen network faults, interpretability, and edge-efficient AI, that are vital for making AI-native telecom infrastructures a reality.”
Seizo Onoe, Director of the ITU Telecommunication Standardization Bureau, stated: “Crowdsourcing new solutions and creating conditions for them to scale, our challenges boost business by helping innovations achieve meaningful impact.”
The competition leverages curated datasets such as TeleLogs and benchmarking frameworks created under the GSMA Open-Telco LLM Benchmarks community, which already maintains a leaderboard tracking LLM performance on telco-specific use cases.
Submissions are currently open and will close on 1 February 2026, with winners to be announced at a prize-giving session during MWC26 Barcelona.
Learn more about the ongoing event here.
Stay updated on the crypto space by following our socials
