Past as a Guide: Leveraging Retrospective Learning for Python Code Completion
This addresses the challenge of enhancing coding capabilities in AI systems, though it appears incremental as it builds on existing LLM methods with a focus on retrospection.
The paper tackles the problem of improving Python code completion by enabling Large Language Models to use past programming and debugging experiences for iterative refinement, achieving a 92% pass@1 on HumanEval.
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.