FasterPy: An LLM-based Code Execution Efficiency Optimization Framework

arXiv:2512.22827 · cs.SE, cs.AI · Submitted 2025-12-28 · Read on arXiv

cs.SE, cs.AI

Submitted: 2025-12-28

Updated: 2026-09-26

Code: https://github.com/WuYue22/fasterpy

Terminology

• Fine-Tuning — 35× in this paper · explained in 5 episodes
• Accuracy — 24× in this paper · explained in 1 episode
• RAG — 24× in this paper · explained in 3 episodes
• Benchmarking — 21× in this paper · explained in 3 episodes
• Benchmark — 17× in this paper · explained in 2 episodes
• Adaptation — 16× in this paper · explained in 1 episode
• Ablation — 15× in this paper · explained in 1 episode
• LoRA Fine-Tuning — 15× in this paper · explained in 3 episodes
• Generalization — 11× in this paper · explained in 13 episodes
• Retrieval-Augmented Generation — 11× in this paper
• Core — 8× in this paper · explained in 2 episodes
• Machine Learning — 8× in this paper
• Ablation study — 7× in this paper · explained in 1 episode
• Semantic Similarity — 7× in this paper · explained in 2 episodes
• Deep Learning — 6× in this paper
• Hallucination — 6× in this paper · explained in 3 episodes
• Retrieval-Augmented Generation (RAG) — 6× in this paper · explained in 16 episodes
• Adaptability — 5× in this paper · explained in 1 episode
• Low-Rank Adaptation (LoRA) — 5× in this paper · explained in 9 episodes
• Reinforcement Learning — 5× in this paper · explained in 4 episodes
• Alignment — 4× in this paper · explained in 1 episode
• Consistency — 4× in this paper · explained in 3 episodes
• Abstract Syntax Tree — 3× in this paper
• Generalizability — 3× in this paper · explained in 6 episodes
• Parameter-Efficient Fine-Tuning — 3× in this paper · explained in 2 episodes
• Semantic Understanding — 3× in this paper · explained in 2 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Computational overhead — 2× in this paper · explained in 2 episodes
• Deep Reinforcement Learning — 2× in this paper · explained in 2 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Knowledge Base Construction — 2× in this paper · explained in 2 episodes
• Performance Improving Code Edits — 2× in this paper
• Robustness — 2× in this paper · explained in 5 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Vector Representations — 2× in this paper · explained in 2 episodes
• World Model — 2× in this paper · explained in 7 episodes
• ACM International Conference on Automated Software Engineering — 1× in this paper
• Approximate Nearest Neighbor — 1× in this paper
• Calibration — 1× in this paper · explained in 7 episodes
• Causal Inference — 1× in this paper · explained in 4 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Conference on Knowledge Discovery and Data Mining — 1× in this paper
• Contextual Understanding — 1× in this paper · explained in 2 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• IEEE Conference on Artificial Intelligence — 1× in this paper
• International Conference on Machine Learning — 1× in this paper
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• LoRA Adaptation — 1× in this paper · explained in 2 episodes
• Multi-Agent Reactive Code Optimizer — 1× in this paper
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Objective Function — 1× in this paper · explained in 2 episodes
• Parameter-Efficient Fine-Tuning (PEFT) — 1× in this paper · explained in 4 episodes
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Transfer Learning — 1× in this paper · explained in 10 episodes
• Zero-Shot Generalization — 1× in this paper · explained in 5 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• Program Synthesis with Large Language Models
• Investigating the Role of Prompting and External Tools in Hallucination Rates of Large Language Models
• A Reinforcement Learning Environment for Automatic Code Optimization in the MLIR Compiler
• Evaluating Large Language Models Trained on Code
• PerfRL: A Small Language Model Framework for Efficient Code Optimization
• Evaluating the effectiveness of LLM-based interoperability
• Towards Better Correctness and Efficiency in Code Generation
• LLM Interactive Optimization of Open Source Python Libraries -- Case Studies and Generalization
• Retrieval-Augmented Generation for Large Language Models: A Survey
• TRACE: Evaluating Execution Efficiency of LLM-Based Code Translation
• DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
• Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey
• Qwen2.5-Coder Technical Report
• A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA
• Learning Performance-Improving Code Edits
• PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback
• MARCO: Multi-Agent Code Optimization with Real-Time Knowledge Integration for High-Performance Computing
• DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
• An Empirical Study on the Performance and Energy Usage of Compiled Python Code
• LLM4EFFI: Leveraging Large Language Models to Enhance Code Efficiency and Correctness

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties