Sep 2026· Proceedings of the 20th ACM Conference on Recommender Systems· pp. 1790-1792· 0 citations· 21 references
Computer Science
TL;DR
AutoRecLab is presented, a Python-based autonomous RecSys lab that automates RecSys experimentation from natural-language prompts that achieves 8 out of 9 successful runs at an average cost of approximately $1 per run using GPT-5.4-mini.
Abstract
Recommender systems (RecSys) research depends on extensive empirical evaluation, yet translating experimental designs into executable code remains a manual, error-prone process. This paper presents AutoRecLab, a Python-based autonomous RecSys lab that automates RecSys experimentation from natural-language prompts. Starting from a research idea, AutoRecLab derives explicit experiment requirements, develops and validates a prototype, and iteratively refines it into the requested full experiment by combining retrieval-augmented generation (RAG) documentation lookup, static type verification, and execution-steered tree search. As a demonstration, AutoRecLab autonomously implements an explicit-to-implicit feedback conversion study and, in a baseline comparison across six algorithms and three datasets, achieves 8 out of 9 successful runs at an average cost of approximately $1 per run using GPT-5.4-mini.
This work presents AutoLR, initially built as Auto Launch Review and later extended upstream into an autonomous research-to-launch harness, which combines three system mechanisms: a multi-expert council that debates and adversarially reviews proposals, a limited trial budget across candidate directions, and a layered k...
Auto-research agents have shown the potential to automate hypothesis generation, experiment execution, and iterative refinement. However, scaling this paradigm to industry-scale recommendation models introduces two challenges: (1) long feedback loops, where model training can take days, making serial iteration prohibit...
Ming Li, Dai-Peng Li, Xu-Ying Ning et al.· 1 citation
Production recommender systems shape what billions of people see, and sustaining their performance requires continual optimization: as content, user behavior, and upstream models shift, the choices governing retrieval, ranking, and serving must be revisited. Traditionally, human engineers test such changes through onli...
Muhammad Azhar, Yu-Hang Zhou, Gilbert Jiang et al.· 1 citation
Modern recommender systems advance not only by scaling data and parameters, but also by encoding task-specific inductive biases through architecture, including sparse feature interactions for click-through rate (CTR) prediction, temporal attention for sequential recommendation, and expert routing for multi-task learnin...
Xiao-Peng Li, Kuo Cai, Bo Chen et al.· 0 citations
FINALLY is a web-based recommender system for dataset selection in RecSys experiments. It supports a decision often made manually or by convention: choosing datasets to evaluate a recommendation algorithm offline. With FINALLY, users choose seed datasets, filters, a target set size, and a recommendation strategy. FINAL...
L. Owie, Tobias Vente, Joeran Beel· Proceedings of the 20th ACM...· 0 citations
As the ACM RecSys Conference marks its 20th anniversary, we believe it is the right time to pause, take inventory, and reflect on what our field might have (inadvertently) overlooked due to its rapid growth and expanding real-world impact. This prompted the 2nd edition of AltRecSys—an alternative, provocative, and expl...
M. S. Pera, Michael D. Ekstrand, Alan Said· Proceedings of the 20th ACM...· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 13, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.
