Unified Search and Recommendation Workshop

Abstract

Search (IR) & recommendation (RecSys) have long been developed in parallel, despite serving the same discovery goal over shared item universes. The rise of LLMs and agentic systems is collapsing this divide, with unified architectures and generative retrieval increasingly powering both query-driven and feed-driven experiences. This workshop brings together researchers and practitioners to accelerate that unification through the first Unified Search and Recommendation Workshop (URSW), held in conjunction with the 20th ACM Conference on Recommender Systems (RecSys 2026) in Minneapolis, Minnesota, USA, in September–October 2026. We aim to define shared tasks & datasets, compare modeling approaches, and align evaluation across intent coverage, generalization, latency/cost, safety, and explainability. Expected outcomes include unification frameworks, benchmarks, reusable resources, and open challenges, aiming to establish unified search-and-recommendation research & practice.