AgentIR: 1st Workshop on Agent-based Information Retrieval

Introduction

Welcome to AgentIR: 1st Workshop on Agent-based Information Retrieval! Information retrieval (IR) systems have become an essential component in modern society to help users find useful information, which consists of a series of processes including query expansion, item recall, item ranking and re-ranking, etc. Based on the ranked information list, users can provide their feedbacks. Such an interaction process between users and IR systems can be naturally formulated as a decision-making problem, which can be either one-step or sequential. In the last ten years, deep reinforcement learning (DRL) has become a promising direction for decision-making, since DRL utilizes the high model capacity of deep learning for complex decision-making tasks. On the one hand, there have been emerging research works focusing on leveraging DRL for IR tasks. However, the fundamental information theory under DRL settings, the challenge of RL methods for Industrial IR tasks, or the simulations of DRL-based IR systems, has not been deeply investigated. On the other hand, the emerging LLM provides new opportunities for optimizing and simulating IR systems.

To this end, we propose the first Agent-based IR workshop at SIGIR 2024, as a continuation from one of the most successful IR workshops, DRL4IR. It provides a venue for both academia researchers and industry practitioners to present the recent advances of both DRL-based IR systems and LLM-based IR systems from the agent-based IR’s perspective, to foster novel research, interesting findings, and new applications. In the last four years, DRL4IR organized at SIGIR’20/21/22 and CIKM’23 was one of the most successful workshops and attracted over 200 workshop attendees each year. In this year, we will pay more attention to fundamental research topics and recent application advances on agent-based IR, with an expectation of over 300 workshop participants.

Call for Papers

We invite submissions related to AgentIR, including (but not limited to):

Off-policy or offline RL in IR scenario
Formulating ranking as a decision-making task
Simulation and Evaluation
DRL for Industrial IRs
LLM-based IRs

Submission Instructions

All submissions (.pdf format) must be written in English and use the latest template of ACM SIGIR 2024 available at http://www.acm.org/publications/proceedings-template. The concepts and keywords are required. Submissions can be of varying length from 4 to 8 pages. References do not count against the page limit. All submissions must be original and not simultaneously submitted to another journal or conference. All submissions will be double-blind peer reviewed by the program committee and judged by their relevance to the workshop, scientific novelty, and technical quality. Please note that at least one of the authors of each accepted paper must register for the workshop and present the paper either remotely or on location (strongly preferred). We encourage but do not require authors to release any code and/or datasets associated with their paper.

Submission website: https://easychair.org/my/conference?conf=agentir2024

Important Dates

Time zone	Anywhere on Earth (AoE)
Acceptance notification	June 15, 2024
Submission deadline	May 15, 2024
AgentIR workshop	July 18, 2024

Attendance

When: July 18, 2024
Where:
- In-person participation: The workshop will be an in-person event and to be held at [TBD].
- Online perticipation: You can also join the workshop virtually at [TBD].