Programme

October 2nd, 2026 — Ballroom 1

8:30 am – 8:35 am Welcome by the organisers

8:35 am – 10:00 am Tutorial: Training and Evaluating LLM Shopping Agents with RecoAtlas.
Flavian Vasile, Otmane Sakhi and Imad Aouali.

10:00 am – 10:30 am Coffee Break

10:30 am – 11:30 am Keynote: Toward Reliable Deployment of LLM Agents: From Uncertainty Quantification to Progress Advantage.

Sharon Li.

11:30 am – 12:00 pm Oral Presentations (12min + 3min Q&A per paper)

• From Prompting to Behavioral Alignment: Personalized LLM Judges for Recommendation Evaluation.
  Alireza Salkhordeh Ziabari, Kat Ellis, Colleen Chan and Ding Tong.

• Following the Eye-Tracking Evidence: Established Web-Search Assumptions Fail in Carousel Interfaces.
  Jingwei Kang, Maarten de Rijke and Harrie Oosterhuis.

12:00 pm – 1:30 pm Lunch Break

1:30 pm – 2:30 pm Keynote: Agent Learning from Rich Feedback. 

   Adith Swaminathan.

2:30 pm – 3:00 pm Oral Presentations (12min + 3min Q&A per paper)

• Off-Policy Evaluation for Semantic ID Recommenders: Does the Model’s Own Code Hierarchy Help?
  Artem Betlei.

• Incremental Recommendation via Causal Models.
  Athanasios Vlontzos, David Gustafsson, Michael O'Riordan and Ciarán Gilligan-Lee.

3:00 pm – 3:30 pm Coffee Break

3:30 pm – 4:00 pm Oral Presentations (12min + 3min Q&A per paper)

• Risk Optimization for Learning to Rank through Portfolio Theory.
  Oscar Ramirez Milian and Harrie Oosterhuis

• Adaptive Doubly Robust Off-Policy Evaluation for Ranking Policies under Diverse User Behavior.
  Kosuke Iguchi and Ren Kishimoto
  
  

4:00 pm – 4:15 pm Closing & Poster Booster slides (1min each) 

4:15 pm – 5:00 pm Poster Session

All times in local time zone of Minnesota, MN, USA (CST, UTC-5).