SWE-Bench 5G: Benchmarking AI Coding Agents on Telecom Network Engineering Tasks
This benchmark addresses the lack of evaluation for AI coding agents in telecom network engineering, a domain with complex runtime dependencies and domain-specific knowledge requirements.
SWE-Bench 5G is the first benchmark for AI coding agents on 5G core network software bugs. Experiments show models diagnose over 91% of bugs but resolve only 10-30%, with domain knowledge from 3GPP specs improving resolution on specification-dependent bugs.
AI coding agents demonstrate strong performance on general-purpose software benchmarks. However, their ability to handle 5G network engineering tasks remains unexplored. We propose SWE-Bench~5G, the first benchmark designed to investigate whether AI coding agents can resolve real-world bugs in 5G core network software. The benchmark collects task instances from three open-source 5G projects, packages each as a self-contained Docker environment with automated fail-to-pass tests, and provides a dual test strategy tailored to the complex runtime dependencies of telecom code. In addition, for instances whose original issues reference 3GPP specification clauses, we construct concise specification context documents, enabling controlled evaluation of whether domain knowledge improves agent performance. Experiments on four LLMs reveal that all models diagnose bugs at rates exceeding 91\%, yet resolve rates remain between 10\% and 30\%, suggesting that both iterative code editing capability and domain knowledge play important roles. The specification injection experiment further confirms that 3GPP excerpts improve resolve rates on specification-dependent bugs, while the gains on generic defensive checks remain limited, indicating that the effect of domain knowledge is conditional on bug type.