The international workshop on Online and Adaptive Recommender Systems (OARS) will serve as a platform for publication and discussion of OARS. It will bring together practitioners and researchers from academia and industry to discuss the challenges and new approaches to implement OARS algorithms and systems and improve user experiences by better modeling and responding to user intent.

Recommender systems (RecSys) play a pivotal role in helping users navigate, discover, and consume massive and ever-changing information. Yet most deployed systems still rely on static user profiles and pre-computed recommendation actions that fail to adapt within or across sessions. As personalization demands intensify, privacy regulations tighten, and user intent grows more dynamic, the need for online and adaptive recommender systems has never been greater.

We invite submission of papers and posters, representing original research, new position and opinion, preliminary results, proposals for new tools, datasets, and resources. All submitted papers will be single-blind and will be peer reviewed by an international program committee of researchers of high repute. Accepted submissions will be presented at the workshop.

🌟 What’s New in 2026

• First time hosted at ACM RecSys
• Focus on agentic AI, memory, and tool-use
• Integration of LLMs with real-time recommendation
• Expanded scope: causal inference & predictive analytics

Topics of interest include, but are not limited to:

Topics

🤖 Agentic & LLM-based RecSys

• Agentic recommender systems, assistants, tool-use
• Semantic IDs, tokenization, multi-modality

⚡ Online Learning

• Reinforcement learning, bandits
• Continual and streaming learning

🧩 System Challenges

• Cold-start, sparsity, distribution shift
• Scalable infrastructure

📊 Evaluation & Theory

• Counterfactual evaluation
• Causal inference
• Fairness and explainability