Workshop on LLM & Agents for Recommendation Systems

Workshop at The ACM Web Conference 2026 (WWW'26) • April 13 - 17, 2026

Workshop at The ACM Web Conference 2026 (WWW'26) • June 29 - July 3, 2026

Workshop Date: June 29 • Virtual • UAE Time zone (GMT+4)

Abstract

Recommendation systems power much of the web economy, influencing how people discover products, content, and services. With the emergence of Large Language Models and autonomous agents, these systems are undergoing a major shift from traditional centralized pipelines to agentic ecosystems that can plan, reason, negotiate, and interact across the entire journey of discovery, personalization, and fulfillment. Large Language Models introduce new capabilities for multimodal reasoning, natural language grounding, and conversational personalization, enabling systems that adapt and respond with greater context and coherence. At the same time, multi agent systems create opportunities for richer collaboration among buyers, sellers, and platforms, while also raising important challenges in interpretability, robustness, governance, and evaluation. Conventional short term metrics such as clicks and conversions are no longer sufficient to measure coordination quality, long horizon impact, trust, or fairness across stakeholders. This workshop brings together researchers and practitioners in recommendation systems, multi agent learning, information retrieval, and mechanism design to explore principles for transparent, scalable, and responsible agent driven personalization. Through contributions on architectures, evaluation, trust, fairness, and real world deployments, the workshop aims to shape the next generation of adaptive, explainable, and societally aligned recommendation ecosystems.

Invited Speakers

Call for Papers

We invite submissions exploring the intersection of Large Language Models (LLMs), intelligent agents, and recommendation systems. This workshop aims to advance the understanding of how LLM-based agents can enhance personalization, user interaction, and decision-making in recommendation systems.

Important Dates

  • Paper Submission Deadline:January 12, 2026
  • Notification of Acceptance:January 26, 2026
  • Camera-Ready Submission:February 2, 2026
  • Workshop Date:June 29, 2026

All deadlines are 11:59 PM Anywhere on Earth (AoE)

Topics of Interest

We welcome research contributions on topics including, but not limited to:

  • LLM-based Recommendation Agents: Design, architecture, and deployment of intelligent recommendation agents
  • Multi-Agent Systems: Coordination, collaboration, and optimization in multi-agent recommendation environments
  • Conversational & Interactive Recommendations: Natural language interfaces, dialogue systems, and user engagement strategies
  • Evaluation & Benchmarking: Novel metrics, datasets, and evaluation frameworks for LLM-based recommenders
  • Personalization & Context-Awareness: Leveraging user context, preferences, and historical data for enhanced personalization
  • Explainability & Transparency: Interpretability of LLM-driven recommendations and building user trust
  • Real-World Applications: Case studies and deployments in e-commerce, content platforms, healthcare, finance, and more
  • Ethical & Societal Implications: Bias, fairness, privacy, and responsible AI in recommendation systems
  • Hybrid Approaches: Combining LLMs with traditional recommender techniques (collaborative filtering, matrix factorization, etc.)
  • Knowledge Graphs & Retrieval-Augmented Generation: Enhancing recommendations with structured knowledge and retrieval mechanisms

Submission Guidelines

Paper Format:

  • Papers should follow the ACM WWW conference format (available at ACM Proceedings Template)
  • Short Papers: 4-6 pages (excluding references)
  • Long Papers: 8-12 pages (excluding references)
  • Submissions must be in PDF format
  • All submissions will undergo single-blind peer review

Submission Portal:

Please submit your papers via our submission portal: Submit Paper on OpenReview

Review Process:

  • Each submission will be reviewed by at least 2 program committee members
  • Reviews will focus on originality, technical quality, relevance, and clarity

Questions?

For any inquiries regarding submissions, please contact the organizing committee at: llmandagents4recsys@googlegroups.com

Accepted Papers

SCORE: Story Coherence and Retrieval Enhancement for AI Narratives
Qiang Yi, Yangfan He, Jianhui Wang, Xinyuan Song, Kuan Lu, ShiYao Qian, Xinhang Yuan, Yi Xin, Yijin Wang, Jingqun Tang, Yuchen Li, Hongyang He, Ernie Tian, Tianxiang Xu, Keqin Li, Menghao Huo, Jiaqi Chen, Miao Zhang, TIANYU SHI, Jianyuan Ni
Smart Book Seeker: Agent-Augmented Retrieval System for Metadata-Sparse Libraries
Hao-Quan Liu, Yao-Chung Fan
LLM-augmented Hybrid Recommendation System for Structured Classification of Customs Commodity Descriptions
Ivan Malashin, Igor Masich, Dmitry Martysyuk, Sergei Kurashkin, Alexey Borodulin, Vladimir Nelyub, Andrei Gantimurov, Vadim Tynchenko
TCR: A Trust-Aligned Text-Only Cross-Attention Ranker Distilling Multimodal LLM Reasoning for Recommendation Agents
Liping Zhang, Tracy Holloway King
AID: Hypothesis-Grounded Probing for Conversational Recommendation
Rajarshee Dhar, Vivek Kumar Singh, Ambrose Taylor, M. David Hanes, Yogesh Ramdoss
HELM: A Human-Centered Evaluation Framework for LLM-Powered Recommender Systems
Sushant Mehta
PCN-Rec: Agentic Proof-Carrying Negotiation for Reliable Governance-Constrained Recommendation
Aradhya Dixit, Shreem Dixit
Ethical Decision-Making under Moral Uncertainty
Djallel Bouneffouf
Triple Modality Fusion: Aligning Visual, Textual, and Graph Data for LLM-based Multi-Behavior Recommender Systems
Luyi Ma, Xiaohan Li, Zezhong Fan, Kai Zhao, Jianpeng Xu, Jason Cho, Praveen Kumar Kanumala, Kaushiki Nag, Evren Korpeoglu, Sushant Kumar, Kannan Achan
Less is More: Benchmarking LLM Based Recommendation Agents
Mahalakshmi Venkateswarlu, Kargi Chauhan
Campaign-2-PT-RAG: LLM-Guided Semantic Product Type Attribution for Scalable Campaign Ranking
Yiming Che, Mansi Ranjit Mane, Keerthi Gopalakrishnan, Parisa Kaghazgaran, Murali Mohana Krishna Dandu, Archana Venkatachalapathy, Sinduja Subramaniam, Yokila Arora, Evren Korpeoglu, Sushant Kumar, Kannan Achan
MATRAG: Multi-Agent Transparent Retrieval-Augmented Generation for Explainable Recommendations
Sushant Mehta
GALRec: Aligning Graph with Large Language Model for Sequential Recommendation
He Lu, Yanting Wang, Haohua Du, Yue Liu, Hanqing Yu
HierFusion: Adaptive Multi-Granularity Fusion for Document Recommendation
Rajarshee Dhar, Vivek Kumar Singh, Ambrose Taylor
LLMs as Orchestrators: Constraint-Compliant Multi-Agent Optimization for Recommendation Systems
Guilin Zhang, Kai Zhao, Jeffrey Friedman, Xu Chu
RobustExplain: Evaluating Robustness of LLM-Based Explanation Agents for Recommendation
Guilin Zhang, Kai Zhao, Jeffrey Friedman, Xu Chu

Schedule

Detailed schedule for the workshop day (tentative) — UAE time (GST, UTC+4) and US Pacific time (PDT, UTC-7):

Time (GST) Time (PDT) Activity Speaker/Details
10:00 – 10:15 11:00 – 11:15 PM (Jun 28) Opening Remarks & Workshop Overview Workshop Organizers
10:15 – 10:45 11:15 – 11:45 PM (Jun 28) Keynote Talk 1 — From Vision to Action: Extracting Structure and Agency from Flat Pixels Prof. Ranjay Krishna
10:45 – 11:15 11:45 PM – 12:15 AM (Jun 28) Keynote Talk 2 — AI that Actions, about Introspection and Delegation Shivani Poddar
11:15 – 11:45 12:15 – 12:45 AM (Jun 29) Keynote Talk 3 — Agentic Audience Simulation for Scientific Evaluation of Recommendation Systems Vasu Sharma
11:45 – 12:15 12:45 – 1:15 AM (Jun 29) Keynote Talk 4 — Beyond Relevance: Interaction Preference, Memory, and UX Evaluation for Agentic Recommender Systems Prof. Hanan Salam
12:15 – 12:35 1:15 – 1:35 AM (Jun 29) Oral Presentation 1 — SCORE: Story Coherence and Retrieval Enhancement for AI Narratives Kuan Lu
12:35 – 12:55 1:35 – 1:55 AM (Jun 29) Oral Presentation 2 — TCR: A Trust-Aligned Text-Only Cross-Attention Ranker Distilling Multimodal LLM Reasoning for Recommendation Agents Liping Zhang
12:55 – 13:15 1:55 – 2:15 AM (Jun 29) Oral Presentation 3 — Less is More: Benchmarking LLM Based Recommendation Agents Mahalakshmi Venkateswarlu, Kargi Chauhan
13:15 – 13:35 2:15 – 2:35 AM (Jun 29) Oral Presentation 4 — AID: Hypothesis-Grounded Probing for Conversational Recommendation Vivek Kumar Singh
13:35 – 13:55 2:35 – 2:55 AM (Jun 29) Oral Presentation 5 — Smart Book Seeker: Agent-Augmented Retrieval System for Metadata-Sparse Libraries Hao-Quan Liu, Yao-Chung Fan
13:55 – 14:15 2:55 – 3:15 AM (Jun 29) Oral Presentation 6 — LLM-augmented Hybrid Recommendation System for Structured Classification of Customs Commodity Descriptions Dr. Igor Masich
14:15 – 14:30 3:15 – 3:30 AM (Jun 29) Closing Remarks & Community Next Steps Workshop Organizers

* Schedule is tentative and subject to change. Fully virtual — no breaks; program runs continuously.

Organizing Committee

Organizing Chairs

* Lead organizers ( Equal Contribution ; Random Order )

Organizing Committee Members (Random order)

Program Committee (Random order)

  • Rong Jin (Chair), Meta Ranking AI
  • Najmeh Forouzandehmehr (Chair), Walmart Global Tech
  • Luke Simon, Meta Ranking AI
  • Keerthi Gopalakrishnan, Walmart Global Tech
  • Zhigang Hua, Meta Ranking AI
  • Aysenur Inan, Walmart Global Tech
  • Qi Xu, Meta Ranking AI
  • Luyi Ma, Walmart Global Tech
  • Jiaxuan You, University of Illinois Urbana-Champaign
  • Prabhat Agarwal, OpenAI
  • Jiliang Tang, Michigan State University
  • Shradha Sehgal, Netflix
  • Shuang Yang, Meta Ranking AI
  • Kai Zhao, Walmart Global Tech
  • Jiyan Yang, Meta Ranking AI
  • Kamilia Ahmadi, Warner Bros. Discovery
  • Hao Wang, Rutgers University
  • Zhuang Liu, Princeton University
  • Fuchun Peng, Meta Ranking AI
  • Yashar Deldjoo, Polytechnic University of Bari
  • Xi Liu, Meta Ranking AI
  • Khadija Khaldi, Meta
  • Hanyu Li, Pinterest
  • Jun Liu, Meta Ranking AI
  • Shreya Singh, Google DeepMind
  • Yi-Ping Hsu, Genova Labs
  • Xiangyi Chen, Pinterest
  • Yihan Cao, LinkedIn