AutoRecLab: Describe the Experiment, Get the Code!

Title:AutoRecLab: Describe the Experiment, Get the Code!

Abstract: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.

Accepted at the 20th ACM Conference on Recommender Systems (RecSys '26), Demo Track. 4 pages, 2 figures

Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG)

arXiv:2609.21863 [cs.AI]

(or arXiv:2609.21863v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2609.21863 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

https://doi.org/10.1145/3773078.3841273 Focus to learn more DOI(s) linking to related resources

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.