Class-Level Code Generation from Natural Language Using Iterative, Tool-Enhanced Reasoning over Repository

LLMs have demonstrated significant potential in code generation tasks, achieving promising results at the function or statement level in various benchmarks. However, the complexities associated with creating code artifacts like classes, particularly within the context of real-world software repositories, remain underexplored. Existing research often treats class-level generation as an isolated task, neglecting the intricate dependencies and interactions that characterize real-world software development environments. To address this gap, we introduce RepoClassBench, a benchmark designed to rigorously evaluate LLMs in generating complex, class-level code within real-world repositories. RepoClassBench includes natural language to class generation tasks across Java and Python, from a selection of public repositories. We ensure that each class in our dataset not only has cross-file dependencies within the repository but also includes corresponding test cases to verify its functionality. We find that current models struggle with the realistic challenges posed by our benchmark, primarily due to their limited exposure to relevant repository contexts. To address this shortcoming, we introduce Retrieve-Repotools-Reflect (RRR), a novel approach that equips LLMs with static analysis tools to iteratively navigate & reason about repository-level context in an agent-based framework. Our experiments demonstrate that RRR significantly outperforms existing baselines on RepoClassBench, showcasing its effectiveness across programming languages and in various settings. Our findings emphasize the need for benchmarks that incorporate repository-level dependencies to more accurately reflect the complexities of software development. Our work illustrates the benefits of leveraging specialized tools to enhance LLMs understanding of repository context. We plan to make our dataset and evaluation harness public.