Two Steps to Precision: Enhancing Reliable API Invocation in Code Generation

ACL ARR 2025 February Submission7975 Authors

Abstract:

Automatic code generation is crucial in modern software development, yet large language models struggle with real-world challenges like code versioning and multi-API invocation.

Existing approaches, including direct generation and retrieval-augmented methods, often fail to ensure precise API usage.

This paper introduces a simple yet effective two-step framework: rough code generation or retrieval followed by fine code editing.

Experiments on VersiCode and BigCodeBench show significant performance gains in version-specific code completion and function-level programming.

These results demonstrate the framework's practicality in enhancing LLM-based code generation systems.

Paper Type: Short

Research Area: NLP Applications

Research Area Keywords: Automatic Code Generation, Two-Step Reasoning, API Invocation Accuracy , Retrieval-Augmented Generation

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 7975