3 papers
cs.LG2026
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…
cs.CL2026
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…
cs.AI2025
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…