PaperCompiler：通过仓库级规范编译实现忠实的论文到代码生成

摘要

将研究论文忠实地转化为仓库级实现仍然充满挑战，因为论文通常仅在高层面上描述方法，对实现假设不做显式说明，同时要求生成的仓库保持方法逻辑、评估协议及跨文件的一致性。尽管论文到代码智能体（paper-to-code agent）近期取得了进展，但其中间输出往往呈现为自由形式的计划或摘要，下游编码智能体可能忽略、重新解读或压缩这些内容，从而导致算法简化及仓库结构不一致。为应对这些挑战，我们提出了PaperCompiler——一个论文到代码生成框架，能够将基于论文的证据编译为显式的仓库级实现规范。PaperCompiler在保留来源出处的同时锚定与实现相关的证据，并区分论文支持的信息、推断的信息、外部委托的信息及未解决的信息。由此生成的规范编码了非降级要求、归属分配、跨文件依赖及文件级约束。仓库生成在此类编译规范的指导下进行，同时保留对论文未限定的局部工程选择的灵活性。PaperCompiler在Paper2CodeBench上优于强基线模型，在基于参考的实现保真度上取得13.8%的相对提升（从3.64提升至4.15），并将高严重性评估批评从13.2%降至6.1%。

English

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%).