PEACE: Towards Efficient Project-Level Efficiency Optimization via Hybrid Code Editing

2025-10-20

AI Summary

Existing LLM-based code efficiency optimization methods operate solely at the function level, ignoring inter-procedural dependencies and thus failing to scale to project-level optimization. This work proposes the first project-level hybrid code editing framework: (1) it constructs a dependency-aware optimization sequence via static dependency analysis; (2) it introduces an effective edit correlation identification mechanism to mitigate spurious edits and suboptimal internal function optimizations; and (3) it implements end-to-end automated optimization through a three-stage iterative pipeline—LLM-driven editing, empirical validity verification, and feedback-guided correction. Evaluated on our curated benchmark PeacExec, the framework achieves a 69.2% pass@1 correctness rate, improves optimization success rate by 46.9%, and delivers an average execution speedup of 0.840×, significantly outperforming state-of-the-art approaches.

Technology Category

• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Constraint Optimization
• Machine Learning: Optimization

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

Large Language Models (LLMs) have demonstrated significant capability in code generation, but their potential in code efficiency optimization remains underexplored. Previous LLM-based code efficiency optimization approaches exclusively focus on function-level optimization and overlook interaction between functions, failing to generalize to real-world development scenarios. Code editing techniques show great potential for conducting project-level optimization, yet they face challenges associated with invalid edits and suboptimal internal functions. To address these gaps, we propose Peace, a novel hybrid framework for Project-level code Efficiency optimization through Automatic Code Editing, which also ensures the overall correctness and integrity of the project. Peace integrates three key phases: dependency-aware optimizing function sequence construction, valid associated edits identification, and efficiency optimization editing iteration. To rigorously evaluate the effectiveness of Peace, we construct PeacExec, the first benchmark comprising 146 real-world optimization tasks from 47 high-impact GitHub Python projects, along with highly qualified test cases and executable environments. Extensive experiments demonstrate Peace's superiority over the state-of-the-art baselines, achieving a 69.2% correctness rate (pass@1), +46.9% opt rate, and 0.840 speedup in execution efficiency. Notably, our Peace outperforms all baselines by significant margins, particularly in complex optimization tasks with multiple functions. Moreover, extensive experiments are also conducted to validate the contributions of each component in Peace, as well as the rationale and effectiveness of our hybrid framework design.

Problem

• Optimizing code efficiency at project level
• Addressing invalid edits in code optimization
• Ensuring correctness in automated code editing

Innovation

• Hybrid framework for project-level code optimization
• Dependency-aware function sequence construction for edits
• Automatic code editing ensuring correctness and integrity