MaxCode: A Max-Reward Reinforcement Learning Framework for Automated Code Optimization

• URL: http://arxiv.org/abs/2601.05475v1
• Date: Fri, 09 Jan 2026 02:21:28 GMT
• Title: MaxCode: A Max-Reward Reinforcement Learning Framework for Automated Code Optimization
• Authors: Jiefu Ou, Sapana Chaudhary, Kaj Bostrom, Nathaniel Weir, Shuai Zhang, Huzefa Rangwala, George Karypis,
• Abstract summary: Large Language Models (LLMs) demonstrate strong capabilities in general coding tasks but encounter two key challenges when optimizing code.<n>In this work, we explore inference-time search algorithms that guide the LLM to discover better solutions.<n>Our approach, called MaxCode unifies existing search methods under a max-reward reinforcement learning framework.
• Score: 44.27213441671799
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) demonstrate strong capabilities in general coding tasks but encounter two key challenges when optimizing code: (i) the complexity of writing optimized code (such as performant CUDA kernels and competition-level CPU code) requires expertise in systems, algorithms and specific languages and (ii) requires interpretation of performance metrics like timing and device utilization beyond binary correctness. In this work, we explore inference-time search algorithms that guide the LLM to discover better solutions through iterative refinement based on execution feedback. Our approach, called MaxCode unifies existing search methods under a max-reward reinforcement learning framework, making the observation and action-value functions modular for modification. To enhance the observation space, we integrate a natural language critique model that converts raw execution feedback into diagnostic insights about errors and performance bottlenecks, and the best-discounted reward seen so far. Together, these provide richer input to the code proposal function. To improve exploration during search, we train a generative reward-to-go model using action values from rollouts to rerank potential solutions. Testing on the KernelBench (CUDA) and PIE (C++) optimization benchmarks shows that MaxCode improves optimized code performance compared to baselines, achieving 20.3% and 10.1% relative improvements in absolute speedup value and relative speedup ranking, respectively.

Related papers

• FasterPy: An LLM-based Code Execution Efficiency Optimization Framework [11.766544835516974]
  Code often suffers from performance bugs.<n>Traditional rule-based methods rely on manually designing and maintaining rules for specific performance bugs.<n>We propose FasterPy, a framework that adapts Large Language Models to optimize the execution efficiency of Python code.
  arXiv  Detail & Related papers  (2025-12-28T07:43:08Z)
• Optimizing Prompt Sequences using Monte Carlo Tree Search for LLM-Based Optimization [20.44067161623662]
  Large language models (LLMs) have demonstrated remarkable capabilities in code generation and structured reasoning.<n>We propose a novel neural-symbolic framework that formulates prompt selection as a sequential decision process guided by Monte Carlo Tree Search.<n>Our method explores and refines multi-step prompt sequences for the goal of improving code generation quality.
  arXiv  Detail & Related papers  (2025-08-08T04:01:24Z)
• CodeDPO: Aligning Code Models with Self Generated and Verified Source Code [52.70310361822519]
  We propose CodeDPO, a framework that integrates preference learning into code generation to improve two key code preference factors: code correctness and efficiency.<n>CodeDPO employs a novel dataset construction method, utilizing a self-generation-and-validation mechanism that simultaneously generates and evaluates code and test cases.
  arXiv  Detail & Related papers  (2024-10-08T01:36:15Z)
• In-context Demonstration Matters: On Prompt Optimization for Pseudo-Supervision Refinement [71.60563181678323]
  Large language models (LLMs) have achieved great success across diverse tasks, and fine-tuning is sometimes needed to further enhance generation quality.<n>To handle these challenges, a direct solution is to generate high-confidence'' data from unsupervised downstream tasks.<n>We propose a novel approach, pseudo-supervised demonstrations aligned prompt optimization (PAPO) algorithm, which jointly refines both the prompt and the overall pseudo-supervision.
  arXiv  Detail & Related papers  (2024-10-04T03:39:28Z)
• Should AI Optimize Your Code? A Comparative Study of Classical Optimizing Compilers Versus Current Large Language Models [0.0]
  Large Language Models (LLMs) raise intriguing questions about the potential of these AI approaches to revolutionize code optimization.<n>This work aims to answer an essential question for the compiler community: "Can AI-driven models revolutionize the way we approach code optimization?"<n>We present a comparative analysis between three classical optimizing compilers and two recent large language models.
  arXiv  Detail & Related papers  (2024-06-17T23:26:41Z)
• Localized Zeroth-Order Prompt Optimization [54.964765668688806]
  We propose a novel algorithm, namely localized zeroth-order prompt optimization (ZOPO) ZOPO incorporates a Neural Tangent Kernel-based derived Gaussian process into standard zeroth-order optimization for an efficient search of well-performing local optima in prompt optimization. Remarkably, ZOPO outperforms existing baselines in terms of both the optimization performance and the query efficiency.
  arXiv  Detail & Related papers  (2024-03-05T14:18:15Z)
• StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback [58.20547418182074]
  We introduce StepCoder, a novel framework for code generation, consisting of two main components. CCCS addresses the exploration challenge by breaking the long sequences code generation task into a Curriculum of Code Completion Subtasks. FGO only optimize the model by masking the unexecuted code segments to provide Fine-Grained Optimization. Our method improves the ability to explore the output space and outperforms state-of-the-art approaches in corresponding benchmarks.
  arXiv  Detail & Related papers  (2024-02-02T13:14:31Z)
• Learning Performance-Improving Code Edits [107.21538852090208]
  We introduce a framework for adapting large language models (LLMs) to high-level program optimization. First, we curate a dataset of performance-improving edits made by human programmers of over 77,000 competitive C++ programming submission pairs. For prompting, we propose retrieval-based few-shot prompting and chain-of-thought, and for finetuning, these include performance-conditioned generation and synthetic data augmentation based on self-play.
  arXiv  Detail & Related papers  (2023-02-15T18:59:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.