7 papers
CTBench: Evaluating Troubleshooting Capabilities of AI Agents in Realistic Telecom Network Operations
Xingyu Yan, Tingting Dai, Antonio De Domenico +16
While autonomous agents show promise for network operations, existing telecom troubleshooting evaluations fail to capture the partial observability and heterogeneity of real-world…
HPO: Hysteretic Policy Optimization for Stable and Efficient Training under Sparse-Reward Regime
Mohamed Sana, Nicola Piovesan, Antonio De Domenico +2
We investigate a narrow but common failure mode of GRPO-style reinforcement learning in the context of sparse verifiable rewards: early updates contain more responses with negative…
TeleTables: A Benchmark for Large Language Models in Telecom Table Interpretation
Anas Ezzakri, Nicola Piovesan, Mohamed Sana +3
Large Language Models (LLMs) are increasingly applied to telecom engineering tasks, yet perform poorly on 3GPP specifications. These standards encode much of their technical inform…
KVCompose: Efficient Structured KV Cache Compression with Composite Tokens
Dmitry Akulov, Mohamed Sana, Antonio De Domenico +3
Large language models (LLMs) rely on key-value (KV) caches for efficient autoregressive decoding; however, cache size grows linearly with context length and model depth, becoming a…
Reasoning Language Models for Root Cause Analysis in 5G Wireless Networks
Mohamed Sana, Nicola Piovesan, Antonio De Domenico +4
Root Cause Analysis (RCA) in mobile networks remains a challenging task due to the need for interpretability, domain expertise, and causal reasoning. In this work, we propose a lig…
TeleMath: A Benchmark for Large Language Models in Telecom Mathematical Problem Solving
Vincenzo Colle, Mohamed Sana, Nicola Piovesan +3
The increasing adoption of artificial intelligence in telecommunications has raised interest in the capability of Large Language Models (LLMs) to address domain-specific, mathemati…
Goal-Oriented Time-Series Forecasting: Foundation Framework Design
Luca-Andrei Fechete, Mohamed Sana, Fadhel Ayed +4
Conventional time-series forecasting methods typically aim to minimize overall prediction error, without accounting for the varying importance of different forecast ranges in downs…