| title | PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compilation |
|---|---|
| authors | Yunhao Liu, Hong Phuc Pham, Jaehong Yoon |
| date | 2026-09-02 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2609.02272 |
| affiliation | Nanyang Technological University Singapore |
| upvotes | 7 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Faithfully translating research papers into repository-level implementations remains challenging because papers often describe methods at a high level, leave implementation assumptions implicit, and require generated repositories to preserve method logic, evaluation protocols, and cross-file consistency. Despite recent advances in paper-to-code agents, their intermediate outputs are often presented as free-form plans or summaries that downstream coding agents may ignore, reinterpret, or compress, leading to algorithmic simplification and inconsistent repository structure. To address these challenges, we introduce PaperCompiler, a paper-to-code generation framework that compiles paper-grounded evidence into explicit repository-level implementation specifications. PaperCompiler grounds implementation-relevant evidence while preserving source provenance and distinguishing paper-supported, inferred, externally delegated, and unresolved information. The resulting specifications encode non-degradation requirements, ownership assignments, cross-file dependencies, and file-level constraints. Repository generation proceeds under these compiled specifications while retaining flexibility over local engineering choices not fixed by the paper. PaperCompiler outperforms strong baselines on Paper2CodeBench, achieving a 13.8% relative improvement in reference-based fidelity (from 3.64 to 4.15) and reducing high-severity evaluator critiques (from 13.2% to 6.1%). |
cite
@misc{liu2026papercompiler,
title={PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compilation},
author={Yunhao Liu and Hong Phuc Pham and Jaehong Yoon},
year={2026},
eprint={2609.02272},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2609.02272}
}