ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation

TL;DR

ReflectionCoder introduces a novel method leveraging reflection sequences with compiler feedback to significantly improve one-off code generation, achieving state-of-the-art results across multiple benchmarks.

Contribution

The paper proposes ReflectionCoder, a new approach that uses reflection sequences and specialized distillation techniques to enhance code generation performance.

Findings

Achieves state-of-the-art performance on HumanEval+, MBPP+, and MultiPL-E benchmarks.

Effectively utilizes reflection sequences through reflection self-distillation.

Demonstrates potential benefits for other domains requiring complex reasoning.

Abstract

Code generation plays a crucial role in various tasks, such as code auto-completion and mathematical reasoning. Previous work has proposed numerous methods to enhance code generation performance, including integrating feedback from the compiler. Inspired by this, we present ReflectionCoder, a novel approach that effectively leverages reflection sequences constructed by integrating compiler feedback to improve one-off code generation performance. Furthermore, we propose reflection self-distillation and dynamically masked distillation to effectively utilize these reflection sequences. Extensive experiments on three benchmarks, i.e., HumanEval (+), MBPP (+), and MultiPL-E, demonstrate that models fine-tuned with our method achieve state-of-the-art performance. Beyond the code domain, we believe this approach can benefit other domains that focus on final results and require long reasoning paths. Code and data are available at https://github.com/SenseLLM/ReflectionCoder.