cs.AI, cs.CL, cs.LG, cs.PL, cs.SE

EffiPair: Improving the Efficiency of LLM-generated Code with Relative Contrastive Feedback

arXiv:2604.05137v1 Announce Type: cross
Abstract: Large language models (LLMs) often generate code that is functionally correct but inefficient in runtime and memory. Prior approaches to improving code efficiency typically rely on absolute execution f…