August 3rd, 2025, Toronto, ON, Canada, KDD 2025
The field of information retrieval has significantly transformed with the integration of AI technologies. AI agents, especially those leveraging LLMs and vast computational power, have revolutionized information retrieval, processing, and presentation. LLM agents, with tool-call, advanced memory, reasoning, and planning capabilities, can perform complex tasks, engage in coherent conversations, and provide personalized responses. Despite these advancements, challenges such as ensuring relevance and accuracy, mitigating biases, providing real-time responses, and maintaining data security remain. This workshop is motivated by the need to explore these challenges, share innovative solutions, and discuss future directions.
Topics Include but not limited to:
Agentic Retrieval System
Agentic Conversational Recommendation
AI Agent for Personalization
AI Agent for Sequential Recommendation
AI Agent for Contextual Information Retrieval
AI Agents for Cross-lingual and Multimodal Retrieval
Retrieval-Augmented Generation Searching System
Optimization of AI Agent Retrieval Models
Bias Mitigation in AI-driven Information Retrieval
Interpretable Generative Retrieval System
Adversarial Attacks and Defenses in Agentic Retrieval System
Ethical Considerations in Agentic Information Retrieval
Human-AI Collaboration in Information Retrieval
Evaluation for Agentic Information Retrieval
Scalability and Efficiency in AI Agent Retrieval
...
Workshop paper submission: 3 June, 2025
Workshop paper notification: 22 June, 2025
Workshop paper camera-ready: 10 July, 2025
Workshop Date: 3 August, 2025
We mainly follow the KDD guidelines for paper submission except for a single-blind peer review. All important guidelines are as follows:
Single-blind peer review. There is no requirements for anonymous submission unless authors prefer.
Full papers cannot exceed 8 pages, including an appendix, plus unlimited references (paper content is limited to 8 pages, that means that if you have an appendix, then it should be included within that page limit. It is also ok if you do not have an appendix and instead 9 pages of content). Short papers cannot exceed 4 pages plus unlimited references.
Formatting Requirements. Submissions must be in English, in double-column format, and must adhere to the ACM template and format (also available in Overleaf). Word users may use the Word Interim Template and the recommended setting for LaTeX is: \documentclass[sigconf, anonymous, review]{acmart}.
Papers should be submitted in PDF format, electronically, using the EasyChair submission system. Ensure submitting to Agent4IR workshop.
Contact: ai4agent@gmail.com
We emphasize that the topics list is not exhaustive and welcome submissions in any related areas. Besides regular research papers, though no need to specify your track during submission, we also welcome other tracks, including
Demo Track, which discusses the designing details about agentic IR systems.
Applied/Industry Track, which investigates applied challenges in agent for IR.
Dataset/Benchmark Track, which introduces new dataset, benchmarks regarding agent for IR.
Note: (1) All submissions to the workshop are non-archival and authors can re-submit to other conferences in the future (2) Each accepted paper needs to have at least one full workshop registration. At Least one author for each accepted paper must be present during the talk to take questions from the audience during the live QA. Please follow the registration link for KDD 2025 registration
Prof. Sanjay Chawla
Chief Scientist, Qatar Computing Research Institute
ex-head & professor , University of Sydney
Prof. Zhou Yu
Columbia University & Co-founder of Arklex.ai , USA
Neil Shah
Principal research scientist, Manager, Snap, USA
Accepted Submissions
Sujitha Pasumarty, Albertsons
Yong Liu, Salesforce
Yu Wang, Netflix
Tianyi Zhang, USC
Ling Yue, Rensselaer Polytechnic Institute
Shengjie Liu, Amazon
Fuheng Zhao, USCB
Connor Lee, New York University
Ze Yang, UIUC
Haifang Li, Mayo Clinic
Deep Narayan Mishra, Walmart, USA
Yuyang Ye, Rutgers University
Contact: ai4agent@gmail.com