# Beyond the Need for Speed: Energy-Aware Code Generation via Simulation-Guided Reinforcement Learning

arXiv: https://arxiv.org/abs/2607.04577 · HTML: https://mlsanity.com/paper/2607.04577/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 64 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [Quantifying the Carbon Emissions of Machine Learning](https://mlsanity.com/paper/1910.09700/) (2019)
- [SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution](https://mlsanity.com/paper/2502.18449/) (2025)
- [CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks](https://mlsanity.com/paper/2105.12655/) (2021)
- [RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning](https://mlsanity.com/paper/2410.02089/) (2024)
- [On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification](https://mlsanity.com/paper/2508.05629/) (2025)
- [A Note on Shumailov et al. (2024): `AI Models Collapse When Trained on Recursively Generated Data'](https://mlsanity.com/paper/2410.12954/) (2024)
- [RLTF: Reinforcement Learning from Unit Test Feedback](https://mlsanity.com/paper/2307.04349/) (2023)
- [A Systematic Review of Green AI](https://mlsanity.com/paper/2301.11047/) (2023)
- [Evaluating Language Models for Efficient Code Generation](https://mlsanity.com/paper/2408.06450/) (2024)
- [EffiBench: Benchmarking the Efficiency of Automatically Generated Code](https://mlsanity.com/paper/2402.02037/) (2024)
- [The Wisdom of Hindsight Makes Language Models Better Instruction Followers](https://mlsanity.com/paper/2302.05206/) (2023)
- [How Efficient is LLM-Generated Code? A Rigorous & High-Standard Benchmark](https://mlsanity.com/paper/2406.06647/) (2024)
- [Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization](https://mlsanity.com/paper/2505.23387/) (2025)
- [Supersonic: Learning to Generate Source Code Optimizations in C/C++](https://mlsanity.com/paper/2309.14846/) (2023)
- [ComPile: A Large IR Dataset from Production Sources](https://mlsanity.com/paper/2309.15432/) (2023)
- [A Controlled Experiment on the Energy Efficiency of the Source Code Generated by Code Llama](https://mlsanity.com/paper/2405.03616/) (2024)
- [AI-Powered, But Power-Hungry? Energy Efficiency of LLM-Generated Code](https://mlsanity.com/paper/2502.02412/) (2025)
- [Learn to Code Sustainably: An Empirical Study on LLM-based Green Code Generation](https://mlsanity.com/paper/2403.03344/) (2024)
- [Enhancing Energy-Awareness in Deep Learning through Fine-Grained Energy Measurement](https://mlsanity.com/paper/2308.12264/) (2023)
- [DRIVE: Data Curation Best Practices for Reinforcement Learning with Verifiable Reward in Competitive Code Generation](https://mlsanity.com/paper/2511.06307/) (2025)
- [Energy-Aware Code Generation with LLMs: Benchmarking Small vs. Large Language Models for Sustainable AI Programming](https://mlsanity.com/paper/2508.08332/) (2025)

## Abstract (arXiv)

Code models strictly prioritize functional correctness, leaving software energy efficiency as an unoptimized byproduct. Training models to generate energy-efficient code requires reproducible feedback at scale, which physical hardware measurement cannot reliably provide due to variance. In this paper, we replace hardware profiling with a deterministic architectural simulation harness to build Green Tea, a corpus of 3.5 million evaluations across 1,474 C++ problems. We train an energy-aware code model via supervised fine-tuning on energy-contrastive pairs, followed by closed-loop reinforcement learning (GRPO) using simulation-in-the-loop feedback. To rigorously evaluate deployment readiness, we introduce the Correctness-Adjusted Reduction in Energy Total (CARET), a metric that explicitly penalizes code that sacrifices functionality for efficiency. On 143 held-out problems, our simulation-in-the-loop pipeline achieves 12.63% CARET, nearly tripling the gain of fine-tuning alone, and successfully beats the energy efficiency of human-expert references on 58.4% of its valid outputs. Furthermore, our analysis exposes the IPC trap: standard throughput proxies like Instructions-Per-Cycle (IPC) actively misrank true energy efficiency on 67.8% of problems, proving the absolute necessity of direct energy simulation. By releasing our dataset and infrastructure, we bypass the 263,000 CPU-hours required for reproduction, structurally empowering the community to deploy inherently energy-efficient code generation models.