# Towards Better Correctness and Efficiency in Code Generation

arXiv: https://arxiv.org/abs/2508.20124 · HTML: https://mlsanity.com/paper/2508.20124/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 19 references that are in the map.
- First posted on arXiv 24 Aug 2025.

## Builds on (most cited first, 11 of 11)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [StarCoder 2 and The Stack v2: The Next Generation](https://mlsanity.com/paper/2402.19173/) (2024)
- [Evaluating Language Models for Efficient Code Generation](https://mlsanity.com/paper/2408.06450/) (2024)
- [ACECode: A Reinforcement Learning Framework for Aligning Code Efficiency and Correctness in Code Language Models](https://mlsanity.com/paper/2412.17264/) (2024)
- [LLM4EFFI: Leveraging Large Language Models to Enhance Code Efficiency and Correctness](https://mlsanity.com/paper/2502.18489/) (2025)

## Built on by (most cited first, 9 of 9)

- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [A Survey on Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2510.10991/) (2025)
- [FasterPy: An LLM-based Code Execution Efficiency Optimization Framework](https://mlsanity.com/paper/2512.22827/) (2025)
- [BranPO: Scalable Contrastive Branch Sampling for Long-Horizon Agentic Reinforcement Learning](https://mlsanity.com/paper/2602.03719/) (2026)
- [Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring](https://mlsanity.com/paper/2605.00754/) (2026)
- [Groupwise Agentic Grading and Advantage Redistribution for Code Agent RL](https://mlsanity.com/paper/2609.32577/) (2026)
- [AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code](https://mlsanity.com/paper/2605.17978/) (2026)
- [Rethinking Code Performance Benchmarks for LLMs](https://mlsanity.com/paper/2607.07619/) (2026)
- [Not All Correct Fixes Run Alike: An Empirical Study of Patch Performance in Repository-Level Issue Resolution](https://mlsanity.com/paper/2610.13563/) (2026)

## Abstract (arXiv)

While code large language models have demonstrated remarkable progress in code generation, the generated code often exhibits poor runtime efficiency, limiting its practical application in performance-sensitive scenarios. To address this limitation, we propose an efficiency-oriented reinforcement learning framework guided by a novel performance reward. Based on this framework, we take a deeper dive into the code efficiency problem, identifying then proposing methods to overcome key bottlenecks: (1) Dynamic exploration overcomes the static data constraints of offline fine-tuning, enabling the discovery of more efficient code implementations. (2) The error-insensitive reinforcement learning method and high-contrast efficiency signals are crucial for mitigating systematic errors and achieving effective optimization. (3) Online exploration is most effective when starting from a high-correctness baseline, as this allows for efficiency improvements without sacrificing accuracy. With these discoveries, we finally propose a two-stage tuning method, which achieves high and balanced performance across correctness and efficiency. The results of experiments show the effectiveness of the method, which improves code correctness by 10.18% and runtime efficiency by 7.75% on a 7B model, achieving performance comparable to much larger model.