In Line with Context: Repository-Level Code Generation via Context Inlining
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915982711193600 |
|---|---|
| author | Hu, Chao Zeng, Wenhao Shi, Yuling Shen, Beijun Gu, Xiaodong |
| author_facet | Hu, Chao Zeng, Wenhao Shi, Yuling Shen, Beijun Gu, Xiaodong |
| contents | Repository-level code generation has attracted growing attention in recent years. Unlike function-level code generation, it requires the model to understand the entire repository, reasoning over complex dependencies across functions, classes, and modules. However, existing approaches such as retrieval-augmented generation (RAG) or context-based function selection often fall short: they primarily rely on surface-level similarity and struggle to capture the rich dependencies that govern repository-level semantics. In this paper, we introduce InlineCoder, a novel framework for repository-level code generation. InlineCoder enhances the understanding of repository context by inlining the unfinished function into its call graph, thereby reframing the challenging repository understanding as an easier function-level coding task. Given a function signature, InlineCoder first generates a draft completion, termed an anchor, which approximates downstream dependencies and enables perplexity-based confidence estimation. This anchor drives a bidirectional inlining process: (i) Upstream Inlining, which embeds the anchor into its callers to capture diverse usage scenarios; and (ii) Downstream Retrieval, which integrates the anchor's callees into the prompt to provide precise dependency context. The enriched context, combining draft completion with upstream and downstream perspectives, equips the LLM with a comprehensive repository view. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_00376 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | In Line with Context: Repository-Level Code Generation via Context Inlining Hu, Chao Zeng, Wenhao Shi, Yuling Shen, Beijun Gu, Xiaodong Software Engineering Artificial Intelligence Repository-level code generation has attracted growing attention in recent years. Unlike function-level code generation, it requires the model to understand the entire repository, reasoning over complex dependencies across functions, classes, and modules. However, existing approaches such as retrieval-augmented generation (RAG) or context-based function selection often fall short: they primarily rely on surface-level similarity and struggle to capture the rich dependencies that govern repository-level semantics. In this paper, we introduce InlineCoder, a novel framework for repository-level code generation. InlineCoder enhances the understanding of repository context by inlining the unfinished function into its call graph, thereby reframing the challenging repository understanding as an easier function-level coding task. Given a function signature, InlineCoder first generates a draft completion, termed an anchor, which approximates downstream dependencies and enables perplexity-based confidence estimation. This anchor drives a bidirectional inlining process: (i) Upstream Inlining, which embeds the anchor into its callers to capture diverse usage scenarios; and (ii) Downstream Retrieval, which integrates the anchor's callees into the prompt to provide precise dependency context. The enriched context, combining draft completion with upstream and downstream perspectives, equips the LLM with a comprehensive repository view. |
| title | In Line with Context: Repository-Level Code Generation via Context Inlining |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2601.00376 |