arXiv subjects

Ali Mamaghani

Publications and source records attributed to Ali Mamaghani.

3 recordsLinked to original sources

arXiv2026

TeleSWEBench: A Commit-Driven Benchmark for Evaluating LLM-Powered Software Engineering in Telecommunications

With the telecommunications field embracing zero touch management alongside novel O-RAN and AI-RAN frameworks, contemporary telecom networks now function as immensely intricate and heavily softwareized codebases. While automated software engineering (ASE) tools and Software Engineering (SWE) Agents hold the potential to alleviate the critical code generation bottleneck in this domain, their ability to navigate and modify specialized, mathematically rigorous wireless stacks like srsRAN 5G remains unverified. General-purpose coding benchmarks fail to capture the stateful logic and strict requirements of telecommunications, leaving a critical evaluation gap. In this paper, we introduce TeleSWEBench, the first commit-driven benchmark specifically designed to measure an agent's performance in the telecom domain. We mine real developer commits from the srsRAN 5G repository and distill them into structured test cases across three difficulty tiers (Easy, Medium, and Difficult). Our benchmark consists of 734 questions that are accompanied by executable unit tests. To avoid the rigidity of test cases, we further propose a hierarchical LLM as a Judge framework called TeleJudge that scores agent outputs at the file level and aggregates verdicts holistically. This follows an evaluation based on context and semantic similarity in parallel to a standard unit test-based evaluation. Using this benchmark, we evaluate AIDER, OpenHands, and the ClaudeCode frameworks, powered by state-of-the-art reasoning LLMs, including Qwen3, GPT OSS, Gemma 4, Kimi, and Qwencoder 2.5. Our two-stage evaluation reveals that models suffer from a lack of both localization accuracy and functional correctness, with the strongest ASE tools achieving up to 25% of shippable changes.

cs.SE↗

arXiv2026

Tiny-Twin: A CPU-Native Full-stack Digital Twin for NextG Cellular Networks

Modern wireless applications demand testing environments that capture the full complexity of next-generation (NextG) cellular networks. While digital twins promise realistic emulation, existing solutions often compromise on physical-layer fidelity and scalability or depend on specialized hardware. We present Tiny-Twin, a CPU-Native, full-stack digital twin framework that enables realistic, repeatable 5G experimentation on commodity CPUs. Tiny-Twin integrates time-varying multi-tap convolution with a complete 5G protocol stack, supporting plug-and-play replay of diverse channel traces. Through a redesigned software architecture and system-level optimizations, Tiny-Twin supports fine-grained convolution entirely in software. With built-in real-time RIC integration and per User Equipment(UE) channel isolation, it facilitates rigorous testing of network algorithms and protocol designs. Our evaluation shows that Tiny-Twin scales to multiple concurrent UEs while preserving protocol timing and end-to-end behavior, delivering a practical middle ground between low-fidelity simulators and high-cost hardware emulators. We release Tiny-Twin as an open-source platform to enable accessible, high-fidelity experimentation for NextG cellular research.

cs.NI↗

arXiv2025

5G Network Automation Using Local Large Language Models and Retrieval-Augmented Generation

This demonstration showcases the integration of a lightweight, locally deployed Large Language Model (LLaMA-3 8b Q-4b) empowered by retrieval augmented generation (RAG) to automate 5G network management, with a strong emphasis on privacy. By running the LLM on local or edge devices ,we eliminate the need for external APIs, ensuring that sensitive data remains secure and is not transmitted over the internet. Although lightweight models may not match the performance of more complex models like GPT-4, we enhance their efficiency and accuracy through RAG. RAG retrieves relevant information from a comprehensive database, enabling the LLM to generate more precise and effective network configurations based on natural language user input. This approach not only improves the accuracy of the generated configurations but also simplifies the process of creating and configuring private networks, making it accessible to users without extensive networking or programming experience. The objective of this demonstration is to highlight the potential of combining local LLMs and RAG to deliver secure, efficient, and adaptable 5G network solutions, paving the way for a future where 5G networks are both privacy-conscious and versatile across diverse user profiles.

cs.NI↗