AgentSearch

As AI agents and tools increasingly perform tasks on behalf of users, the digital ecosystem is rapidly filling with dynamic, task-oriented systems that offer overlapping capabilities. This shift raises a fundamental question: how can users and orchestrating systems reliably discover, compare, and select the most appropriate agents for a given task? AgentSearch frames this challenge as a first-class information retrieval problem. Unlike traditional IR, where static documents are retrieved, agent search involves dynamic entities whose suitability depends on capabilities, behavior, reliability, constraints, and task-dependent performance. This workshop brings together researchers and practitioners to develop principled methods for indexing, retrieving, ranking, and evaluating AI agents and tools, establishing a coherent research agenda at the intersection of information retrieval and agentic systems.

The workshop features an interactive format including keynotes, panel discussions, breakout sessions, and poster presentations.

The first workshop on Indexing, Retrieval, and Ranking of AI Agents is accepting submissions that describe original research findings, preliminary research results, proposals for new work, and recent relevant studies already published in high-quality venues.

Submission Types

We welcome various types of submissions:

• Research Papers: Original or recently published research on indexing, retrieval, and ranking of AI agents. We welcome any topic within the scope of the workshop. Submissions may follow the short or full paper format (following the SIGIR track guidelines).
  Any length between 4 and 9 pages (excluding references).
• Extended Abstracts: A concise summary of work in progress or preliminary findings, outlining the main contribution and approach.
  At most 2 pages (excluding references).
• Perspective Papers: New perspectives on AgentSearch that suggest future directions and research opportunities grounded in the current literature. Experiments are not required, but we encourage including motivating experiments to support the claims. A good perspective paper follows the SIGIR perspectives track guidelines.
  At most 9 pages (excluding references).
• Demo Papers: Papers that showcase the capabilities of systems that support agent search. Code submissions are not required but are highly encouraged. A good demo paper follows the SIGIR demonstrations track guidelines.
  At most 4 pages (excluding references).

Submission Instructions

Page limit does not include references. All content, including any appendix, must fit within the page limit. Note that we care more about the quality of the submission and its potential to spur discussion at the workshop than about page length as long as the paper meets the page limits.

At least one author of each accepted paper must register for the workshop and present the paper in person (strongly preferred) or remotely.

We encourage, but do not require, authors to release any code and/or datasets associated with their paper.

All submissions must be in PDF format and written in English. Please use the SIGIR 2026 template (ACM two-column format). For LaTeX, the following should be used:
\documentclass[sigconf,natbib=true,review]{acmart}

All submissions will be single-blind reviewed. Submissions should be made through EasyChair: https://easychair.org/conferences/?conf=agentsearch2026.

Note: This is a non-archival workshop. Accepted papers will be made available on the workshop website, but authors retain full copyright and are free to submit to other venues.