用契约机制让AI精准复现论文代码，解决信息丢失难题。
ReproAgent: Contract-Guided Paper-to-Code Reproduction
- 构建四阶段流程，通过双通道契约追踪代码要求与证据
- 在PaperBench上达同架构最高均分，支持端到端验证
- 适合需要可复现研究的AI开发者与学术团队
论文到代码的复现要求科学AI代理将研究论文转化为可执行仓库，以完整保留方法、协议和实验成果。该任务困难源于信息分散：显式内容（如算法、指标、产物）常在长轨迹中丢失，隐式细节（如框架默认值、继承自相关工作的惯例）则未在论文中明确说明。本文提出ReproAgent，一个围绕持久化实施契约的四阶段流程（准备-规划-生成-修复），包含两个通道：实现需求通道将论文片段转化为代码责任，参考证据通道从相关仓库检索内容与结构证据。两个通道绑定至工作包，投影为文件级契约，在生成与修复过程中持续使用。在PaperBench Code-Dev测试集上，ReproAgent在Claude-Sonnet-4.5与Gemini-3-Flash同基础模型下达到最高均分。端到端通道消融实验及逐篇案例分析证实了双通道贡献。代码与实验产物已公开。
原文摘要 · Abstract (English)
Paper-to-code reproduction asks scientific AI agents to turn research papers into executable repositories that preserve the paper's method, protocol and artifacts. This is difficult because the specification is split: explicit paper content such as algorithms, metrics and artifacts is often lost across long agent trajectories, while implicit details such as framework defaults and conventions inherited from related work are absent from the paper. We introduce ReproAgent, a four-stage Prepare--Plan--Generate--Repair pipeline built around a persistent implementation contract with two channels: an implementation-requirement channel that turns paper snippets into code obligations, and a reference-evidence channel that retrieves content and structure evidence from related repositories. Both are bound to work packages, projected into file-level contracts, and consumed across generation and repair. On PaperBench Code-Dev, ReproAgent reaches the highest mean score among same-backbone scaffolds under both Claude-Sonnet-4.5 and Gemini-3-Flash. End-to-end channel ablations and per-paper cases support the contribution of both channels. Code and experimental artifacts are publicly available.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。