ReproAgent: Contract-Guided Paper-to-Code Reproduction

2026-08-25

AI Summary

研究解决了论文到代码复现难题，通过引入ReproAgent，一个基于持续实现合同的四阶段管道，利用实现需求和参考证据两个通道来生成和修复代码。

Abstract

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.

Problem

• Paper-to-Code Reproduction
• Implementation Contract
• Explicit Paper Content
• Implicit Details

Innovation

• Contract-Guided
• Paper-to-Code Reproduction
• Implementation Contract
• Persistent Channels
• Generate--Repair Pipeline