Personalization is being rebuilt around generative models. Large language models, retrieval-augmented generation, and agentic systems are transforming how recommender systems retrieve, rank, explain, converse with, and even simulate users — while surfacing hard new challenges around hallucination, controllability, evaluation, privacy, fairness, and long-term user impact.
GRAIL 2026 is a workshop at CIKM 2026 dedicated to generative recommender systems: methods that use generative models for retrieval, ranking, planning, and explanation, as well as for conversational agents, user simulation, and evaluation. It brings academic researchers and industry practitioners together to push these approaches forward while giving equal attention to their reliability, safety, and responsible deployment.
Whether you build, study, or deploy recommender systems, we invite you to take part. See the Call for Papers for topics and submission details, and join us in Rome on November 8, 2026.
GRAIL 2026 welcomes original research, position pieces, and practical contributions at the intersection of generative AI and personalization. Topics include, but are not limited to:
Mature research results. Maximum 8 pages, plus unlimited pages for references, appendix, and GenAI-usage disclosure.
Ongoing work, demos, position, or opinion papers. Maximum 4 pages, plus unlimited pages for references, appendix, and GenAI-usage disclosure.
All submissions follow the standard ACM double-column template. Each paper receives at least three reviews. Papers are non-archival, so authors remain free to submit revised versions elsewhere. At least one author of each accepted paper must register and present in person in Rome. Submissions are handled via EasyChair.
Following the ACM publication workflow, all manuscripts must be submitted for review in the standard ACM double-column format. Use the latest official ACM templates:
The recommended setting for LaTeX documents is: \documentclass[sigconf, review]{acmart}
Review process: GRAIL 2026 uses single-blind review. Authors should include their names and affiliations in the submission — anonymization is not required.
All deadlines are 11:59 PM Anywhere on Earth (AoE).
GRAIL 2026 is organized by a team spanning academia and industry.
Full Professor, Department of Computer, Control and Management Engineering, Sapienza University of Rome
Sunday, November 8, 2026 · 09:00–13:00 · Half-day, in-person
Venue: San Pietro in Vincoli Campus, Sapienza University of Rome — Faculty of Engineering, Via Eudossiana 18, 00184 Roma (venue details & directions)
For questions about the workshop, please contact the organizing team at grail2026-cikm@googlegroups.com, or reach out to Ashish Jain directly at ashish.jain@airbnb.com.
