# ReproAgent: Contract-Guided Paper-to-Code Reproduction

arXiv: https://arxiv.org/abs/2608.24291 · HTML: https://mlsanity.com/paper/2608.24291/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 37 references that are in the map.
- First posted on arXiv 25 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024)
- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)](https://mlsanity.com/paper/2003.12206/) (2020)
- [DocPrompting: Generating Code by Retrieving the Docs](https://mlsanity.com/paper/2207.05987/) (2022)
- [CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark](https://mlsanity.com/paper/2409.11363/) (2024)
- [Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning](https://mlsanity.com/paper/2504.17192/) (2025)
- [SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers](https://mlsanity.com/paper/2504.00255/) (2025)
- [Dataflow-Guided Retrieval Augmentation for Repository-Level Code Completion](https://mlsanity.com/paper/2405.19782/) (2024)
- [AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage](https://mlsanity.com/paper/2505.20662/) (2025)
- [LMR-BENCH: Evaluating LLM Agent's Ability on Reproducing Language Modeling Research](https://mlsanity.com/paper/2506.17335/) (2025)
- [AutoP2C: An LLM-Based Agent Framework for Code Repository Generation from Multimodal Content in Academic Papers](https://mlsanity.com/paper/2504.20115/) (2025)
- [GraphCodeAgent: Dual Graph-Guided LLM Agent for Retrieval-Augmented Repo-Level Code Generation](https://mlsanity.com/paper/2504.10046/) (2025)
- [Toward Autonomous Long-Horizon Engineering for ML Research](https://mlsanity.com/paper/2604.13018/) (2026)
- [DocCGen: Document-based Controlled Code Generation](https://mlsanity.com/paper/2406.11925/) (2024)
- [Reflective Paper-to-Code Reproduction Enabled by Fine-Grained Verification](https://mlsanity.com/paper/2508.16671/) (2025)
- [SciCoQA: Quality Assurance for Scientific Paper--Code Alignment](https://mlsanity.com/paper/2601.12910/) (2026)
- [DLPaper2Code: Auto-generation of Code from Deep Learning Research Papers](https://mlsanity.com/paper/1711.03543/) (2017)
- [HiRAS: A Hierarchical Multi-Agent Framework for Paper-to-Code Generation and Execution](https://mlsanity.com/paper/2604.17745/) (2026)

## Built on by (most cited first, 1 of 1)

- [RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?](https://mlsanity.com/paper/2609.28850/) (2026)

## Abstract (arXiv)

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.