←
AgentSearch10 posts
AgentSearch avatar

AgentSearch

@AgentSearchIR

AI agents as first-class retrieval targets. AgentSearch Workshop @SIGIR2026.

◷ Joined February 2026▧ 1 Photos and videos
AgentSearch avatar
AgentSearch@AgentSearchIR·Sep 15

New survey on Agent and Tool Search—an excellent foundation for our community. Our SIGIR 2026 Workshop on Agent Search has finished, while the Agent Search Challenge is ongoing. 🌐 Workshop: agent-search.github.io/agent… 🏆 Challenge: agent-search.github.io/agent… #AgentSearch #SIGIR2026

🚀 Our survey, “Agent and Tool Search: Foundations, Techniques, and Open Challenges,” is out! 📄 Paper: openreview.net/pdf?id=lk32qf… 💻 Literature collection: github.com/Bingo-W/Awesome-A… How can we choose suitable agents and tools as agent ecosystems grow? 🧵

Post attachmentPost attachment
AgentSearch avatar
AgentSearch@AgentSearchIR·Apr 28

Excited to see momentum in agent search research 🚀 Interested in this area? Submit to AgentSearch @ SIGIR 2026 📅 Deadline: May 8 (AoE) agent-search.github.io/agent…

🚀 New paper: AgentSearchBench — a benchmark for AI agent search in the wild. As agent ecosystems grow, a fundamental question emerges: how do we find the right agent for a task? We build a benchmark with ~10k real-world agents and show: • Semantic similarity ≠ agent performance • Description-based ranking often underestimates capable agents • Execution-aware probing improves ranking 📄 Paper: arxiv.org/abs/2604.22436 Joint work with Arastun Mammadli @arastunmammadli (co-first author) and Xiaoyu Zhang, Emine Yilmaz @emine_yilm at the UCL AI Center @ai_ucl and UCL Computer Science @uclcs #AI #Agents #LLM #InformationRetrieval

AgentSearch avatar
AgentSearch@AgentSearchIR·Apr 22

Submission Types - Extended abstracts: up to 2 pages (excluding references) - Research, perspective, and demo papers: 4–9 pages (excluding references)

AgentSearch avatar
AgentSearch@AgentSearchIR·Apr 22

Topics include (but are not limited to) - Representation and discovery of agents/tools - Retrieval, ranking, and recommendation of agents/tools - Evaluation and benchmarking for agent/tool search - Responsible and human-centered agent/tool search

AgentSearch avatar
AgentSearch@AgentSearchIR·Mar 13

We invite submissions on topics including: • Agent/tool discovery • Retrieval & ranking of agents • Evaluation & benchmarking • Responsible & human-centered agent search Submissions: extended abstracts (2p) or research/perspective/demo papers (4–9p).

Bin Wu avatar
⟳ AgentSearch retweeted
Bin Wu@binwu_cs·Mar 2

🚀 AgentSearch Workshop @ ACM SIGIR ’26 We’re excited to announce AgentSearch: The First Workshop on Indexing, Retrieval, and Ranking of AI Agents, co-located with ACM SIGIR 2026 (Melbourne | Naarm, Australia). As AI agents rapidly proliferate, how can users, developers, and multi-agent systems reliably identify and select the "right" agents or tools for a given task? 🌐 agent-search.github.io/agent… 🐦 @AgentSearchIR 🦋 bsky.app/profile/agentsearch… Organizers: Bin Wu @binwu_cs (University College London), To Eun Kim @TEKnologyy (Carnegie Mellon University), Yue Feng @YueFeng__ (University of Birmingham), Fernando Diaz @841io (Carnegie Mellon University), Zhaochun Ren @zhaochun_ren (Leiden University), Emine Yilmaz @emine_yilm (University College London & Amazon) #SIGIR #SIGIR2026 #InformationRetrieval #AIAgents #MultiAgents #AgentSearch