发表机构
University of Siegen; University of Göttingen（锡根大学; 哥廷根大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
AutoRecLab是一个基于Python的自主推荐系统实验室，能从自然语言描述自动生成实验代码，结合RAG、静态类型验证和树搜索，在演示中成功实现反馈转换研究，8/9次运行成功，每次成本约1美元。
AI 中文摘要
经验评估是推荐系统（RecSys）研究的核心，但将实验设计转化为可执行代码仍然是一项手动且易出错的任务。我们提出了AutoRecLab，一个基于Python的自主推荐系统实验室，它能够从自然语言提示中自动化推荐系统实验。给定一个研究想法，AutoRecLab会推导出明确的实验需求，构建并验证原型，然后迭代地将其扩展为所要求的完整实验。该工作流程结合了用于文档查找的检索增强生成（RAG）、静态类型验证以及执行引导的树搜索。在我们的演示中，AutoRecLab自主实现了一项显式到隐式反馈转换研究。在跨六个算法和三个数据集的基线比较中，9次运行中有8次成功，使用GPT-5.4-mini时平均每次运行成本约为1美元。
英文摘要
Empirical evaluation is central to recommender-systems (RecSys) research, but turning experimental designs into executable code remains a manual and error-prone task. We present AutoRecLab, a Python-based autonomous RecSys lab that automates RecSys experiments from natural-language prompts. Given a research idea, AutoRecLab derives explicit experiment requirements, builds and validates a prototype, and iteratively expands it into the requested full experiment. The workflow combines retrieval-augmented generation (RAG) for documentation lookup, static type verification, and execution-steered tree search. In our demonstration, AutoRecLab autonomously implements an explicit-to-implicit feedback conversion study. In a baseline comparison across six algorithms and three datasets, 8 of 9 runs succeed at an average cost of approx- imately $1 per run with GPT-5.4-mini.
CommentsAccepted at the 20th ACM Conference on Recommender Systems (RecSys '26), Demo Track. 4 pages, 2 figures
