Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization

Mingzhe Du, Anh Tuan Luu, Yue Liu, Yuhao QING, Dong HUANG, Xinyi He, Qian Liu, Zejun MA, See-Kiong Ng

Keywords: Code Generation

TL;DR: This paper introduces an iterative optimization framework that leverages real-time execution feedback to improve code efficiency.

Track: Long Paper (up to 9 pages)

Abstract: Large Language Models (LLMs) generate functionally correct solutions but often fall short in code efficiency, a critical bottleneck for real-world deployment. In this paper, we introduce a novel test-time iterative optimization framework to address this, employing a closed-loop system where LLMs iteratively refine code based on empirical performance feedback from an execution sandbox. We explore three training strategies: Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Group Relative Policy Optimization~(GRPO). Experiments on our Venus dataset and the APPS benchmark show that SFT and DPO rapidly saturate in efficiency gains. In contrast, GRPO, using reinforcement learning (RL) with execution feedback, continuously optimizes code performance, significantly boosting both pass@1 (from 47% to 62%) and the likelihood of outperforming human submissions in efficiency (from 31% to 45%). Our work demonstrates effective test-time code efficiency improvement and critically reveals the power of RL in teaching LLMs to truly self-improve code efficiency.

Format: We have read the camera-ready instructions, and our paper is formatted with the provided template.

De-Anonymization: This submission has been de-anonymized.

Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.

Submission Number: 18