Toward Executable Repository-Level Code Generation via Environment Alignment

TL;DR

This paper introduces EnvGraph, a novel framework for repository-level code generation that aligns environment conditions to ensure executable, installable, and valid multi-file repositories using large language models.

Contribution

EnvGraph formulates repository executability as an environment alignment problem, jointly modeling dependency satisfaction and internal reference resolution for improved code generation.

Findings

EnvGraph outperforms baseline methods in functional correctness.

It achieves 5.72-5.87% higher functional correctness.

It improves non-functional quality by 4.58-8.66%.

Abstract

Large language models (LLMs) have achieved strong performance on code generation, but existing methods still struggle with repository-level code generation under executable validation. Under this evaluation setting, success is determined not by the plausibility of isolated code fragments, but by whether a generated multi-file repository can be successfully installed, have its dependencies and internal references resolved, be launched, and be validated in a real execution environment. To address this challenge, we propose EnvGraph, a framework for repository-level code generation that formulates repository executability as an environment alignment problem. EnvGraph jointly models two coupled conditions for successful repository execution, namely external dependency satisfaction and repository-internal reference resolution. It maintains a dual-layer environment representation, uses execution evidence to perform execution-evidence-based attribution, and guides repository generation through a unified targeted revision mechanism within an iterative alignment loop. We evaluate EnvGraph on repository-level code generation with three representative backbone LLMs and compare it against representative environment-aware and repository-level baselines. Experimental results show that EnvGraph consistently achieves the best performance on these repository-level benchmarks. In particular, it outperforms the strongest non-EnvGraph baseline by an absolute margin of 5.72--5.87 percentage points in Functional Correctness and 4.58--8.66 percentage points in Non-Functional Quality.