Self-Guided Planning and Repair Framework for Code Generation (Student Abstract)

Abstract

Large Language Models (LLMs) demonstrate strong capabilities in code generation but often lack adaptability in planning and refinement. We propose Self-PR, a framework that integrates adaptive plan selection and iterative repair to improve correctness and generalization. Self-PR constructs a reusable plan database via task clustering and trains a selector to choose task-specific strategies. Incorrect outputs are refined through multi-round feedback until correctness. Trained only on HumanEval, Self-PR generalizes well to out-of-distribution tasks (MBPP), improving pass@1 by +4.9% on HumanEval and +5.5% on MBPP compared to Modularization-of-Thought prompting. Experiments across Llama-3 (8B, 70B) and GPT-4o-mini confirm robustness and scalability. These findings suggest that adaptive planning and feedback-driven repair are essential for reliable LLM-based code generation.