AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage

ACL ARR 2026 January Submission5717 Authors

Keywords: large Language Models, Code Generation

Abstract:

Efficient reproduction of research papers is pivotal to accelerating scientific progress. However, the increasing complexity of proposed methods often renders reproduction a labor-intensive endeavor, necessitating profound domain expertise.
To address this, we introduce the paper lineage, which systematically mines implicit knowledge from the cited literature. This algorithm serves as the backbone of our proposed \ours, a multi-agent framework designed to autonomously reproduce experimental code in a complete, end-to-end manner. To ensure code executability, \ours incorporates a sampling-based unit testing strategy for rapid validation. To assess reproduction capabilities, we introduce \ourbench, a benchmark featuring verified implementations, alongside comprehensive metrics for evaluating both reproduction and execution fidelity. Extensive evaluations on PaperBench and \ourbench demonstrate that \ours consistently surpasses existing baselines across all metrics. Notably, it yields substantial improvements in reproduction fidelity and final execution performance. The code and benchmark will be released soon.

Paper Type: Long

Research Area: AI/LLM Agents

Research Area Keywords: LLM/AI agents, code generation and understanding, agent evaluation

Contribution Types: NLP engineering experiment, Reproduction study

Languages Studied: English

Submission Number: 5717