Paper Accepted at ICSE 2026

We are excited to announce that a paper by S2 members and their colleagues has been accepted at International Conference on Software Engineering (ICSE) 2026, one of the premier conferences in software engineering research!

Title: Generating Energy-Efficient Code via Large-Language Models – Where are we now?

Authors: Radu Apsan, Vincenzo Stoico, Michel Albonico, Rudra Dhar, Karthik Vaidhyanathan, and Ivano Malavolta.

🔗 Read the paper here

🔬 Study Highlights

🐍 We measure the energy usage of Python code generated by LLMs compared to human-written code.

🤖 We evaluate 363 solutions to 9 coding problems from the EvoEval benchmark using 6 LLMs with 4 prompting techniques, comparing them to human-developed solutions.

💻 The evaluation spans 3 hardware platforms: a server, a PC, and a Raspberry Pi — totaling over 36 days of experimentation.

💡 Key Findings

• 🟢 Human expert code remains the most energy-efficient, outperforming all LLM-generated code by 17% to 30%.

• 🤖 LLMs outperform average human developers on some platforms, but still lag behind green-expert solutions.

• ⚙️ Prompt engineering does not consistently improve energy efficiency.

• 🌩️ Human expertise is still crucial for developing energy-efficient Python code.