用AI工具自动优化已有算法实现，11次实验全成功且一天内完成。
Applying an Agentic Coding Tool for Improving Published Algorithm Implementations
- 分两阶段：先找新算法，再让AI迭代改进代码
- 11个实验全部提升性能，单日即可完成优化
- 适合研究人员快速验证与改进论文实现
我们提出一种两阶段的AI辅助方法，用于改进已发表的算法实现。第一阶段由具备研究能力的大语言模型识别满足特定实验条件的最新算法；第二阶段将提示输入Claude Code，使其复现基准实现并进行迭代优化。该方法应用于多个研究领域的已发表算法，所有11项实验均取得改进，每项改进可在单个工作日内完成。我们分析了仍需人类参与的关键环节，包括目标选择、实验有效性验证、创新性与影响评估、计算资源提供以及适当披露AI使用情况。最后讨论了对同行评审与学术出版的影响。
原文摘要 · Abstract (English)
We present a two-stage pipeline for AI-assisted improvement of published algorithm implementations. In the first stage, a large language model with research capabilities identifies recently published algorithms satisfying explicit experimental criteria. In the second stage, Claude Code is given a prompt to reproduce the reported baseline and then iterate an improvement process. We apply this pipeline to published algorithm implementations spanning multiple research domains. Claude Code reported that all eleven experiments yielded improvements. Each improvement could be achieved within a single working day. We analyse the human contributions that remain indispensable, including selecting the target, verifying experimental validity, assessing novelty and impact, providing computational resources, and writing with appropriate AI-use disclosure. Finally, we discuss implications for peer review and academic publishing.
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。