Laura Duits

Laura Duits, Bouazza El Moutaouakil, Ivano Malavolta

Context. The most used development framework for robotics software is ROS2. ROS2 architectures are highly complex, with thousands of components communicating in a decentralized fashion. Goal. We aim to evaluate how LLMs can assist in the comprehension of factual information about the architecture of ROS2 systems. Method. We conduct a controlled experiment where we administer 1,230 prompts to 9 LLMs containing architecturally-relevant questions about 3 ROS2 systems with incremental size. We provide a generic algorithm that systematically generates architecturally-relevant questions for a ROS2 system. Then, we (i) assess the accuracy of the answers of the LLMs against a ground truth established via running and monitoring the 3 ROS2 systems and (ii) qualitatively analyse the explanations provided by the LLMs. Results. Almost all questions are answered correctly across all LLMs (mean=98.22%). gemini-2.5-pro performs best (100% accuracy across all prompts and systems), followed by o3 (99.77%), and gemini-2.5-flash (99.72%); the least performing LLM is gpt-4.1 (95%). Only 300/1,230 prompts are incorrectly answered, of which 249 are about the most complex system. The coherence scores in LLM's explanations range from 0.394 for "service references" to 0.762 for "communication path". The mean perplexity varies significantly across models, with chatgpt-4o achieving the lowest score (19.6) and o4-mini the highest (103.6). Conclusions. There is great potential in the usage of LLMs to aid ROS2 developers in comprehending non-trivial aspects of the software architecture of their systems. Nevertheless, developers should be aware of the intrinsic limitations and different performances of the LLMs and take those into account when using them.

Vlad-Andrei Cursaru, Laura Duits, Joel Milligan et al.

Context. Nowadays, 83% of software developers use Large Language Models (LLMs) to generate code. LLMs recently became essential to increase the productivity of software developers and decrease the time and cost of software development. Developers ranging from novices to experts use LLM tools not only to detect and patch bugs, but also to integrate generated code into their software. However, as of today there is no objective assessment of the energy efficiency of the source code generated by LLM tools. Released in August 2023, Code Llama is one of the most recent LLM tools. Goal. In this paper, we present an empirical study that assesses the energy efficiency of Code Llama with respect to human-written source code. Method. We design an experiment involving three human-written benchmarks implemented in C++, JavaScript, and Python. We ask Code Llama to generate the code of the benchmarks using different prompts and temperatures. Therefore, we execute both implementations and profile their energy efficiency. Results. Our study shows that the energy efficiency of code generated by Code Llama is heavily-dependent on the chosen programming language and the specific code problem at hand. Also, human implementations tend to be more energy efficient overall, with generated JavaScript code outperforming its human counterpart. Moreover, explicitly asking Code Llama to generate energy-efficient code results in an equal or worse energy efficiency, as well as using different temperatures seems not to affect the energy efficiency of generated code. Conclusions. According to our results, code generated using Code Llama does not guarantee energy efficiency, even when prompted to do so. Therefore, software developers should evaluate the energy efficiency of generated code before integrating it into the software system under development.