Past as a Guide: Leveraging Retrospective Learning for Python Code Completion

Seungyoun Shin, Seunggyu Chang, Sungjoon Choi

Keywords: interactive and iterative code refinements, retrospection, Large Language Model

TL;DR: PaG enhances LLM's code completion by using past experiences and iterative refinements. It merges memory retrieval and refinements without external correctness feedback. In tests, PaG achieved a 92% pass@1 on HumanEval, surpassing other methods.

Abstract:

This work presents Past as a Guide (PaG), a simple approach for Large Language Models (LLMs) to improve the coding capabilities by integrating the past history with interactive and iterative code refinements.
To be specific, inspired by human cognitive processes, the proposed method enables LLMs to utilize previous programming and debugging experiences to enhance the Python code completion tasks.
The framework facilitates LLMs to iteratively refine the Python code based on previous execution and debugging results and optimize learning and reasoning capabilities.
The proposed methodology achieved a 92\% pass@1 on HumanEval, demonstrating the potential to advance the field by leveraging retrospection from past experiences and interactive and iterative refinement processes without external correctness indicators.

Submission Number: 59