Hi — curious minds of the internet. I am Saber Zerhoudi, currently an Information Retrieval research scientist, based in Passau, Germany. My current research focuses on user simulation, user-centric evaluation of interactive search systems, and agentic AI.

Previously, I earned my Ph.D. at University of Passau, where I contributed to the OpenWebSearch project on large-scale, distributed web crawling and the creation of an open web index, and to the SINIR project on simulation-based evaluation of interactive search behavior in digital libraries.

I'm a user simulation and search researcher. I'm broadly interested in how we can evaluate and design information access systems from a user-centric perspective, especially now that generative models and agents are part of the picture. My work falls into three interconnected themes:

  • User Simulation: I develop user simulators to model search behavior in classic and conversational settings. Notable contributions include SimIIR 2.0, SimIIR 3, and UXSim. These modular frameworks extend previous work by integrating LLM-based components and hybrid cognitive layers with traditional methods. They provide a unified testbed for systematic experimentation across diverse user types, interfaces, and tasks.

  • Open Web Crawling & Indexing: I help design and operate large-scale crawling pipelines and infrastructure for the European Open Web Index, this involves the Open Web Search Crawler (OWLer) and its ecosystem for distributed, efficient crawling. Furthermore, I contribute to services exposing the Open Web Index for search, analytics, and generative AI applications.

  • User-Centric RAG & Agents: I investigate agent-based retrieval-augmented generation systems that adapt to users. A central framework is PersonaRAG, which employs agents to analyze interactions and maintain user personas. This approach guides retrieval and generation processes to provide personalized, stable answers for complex questions.

Additionally, I also founded and maintain SearchSim, a small community hub that curates work on user-centric search simulation and provides TL;DR-style updates on new papers and resources.

Program Committees & Reviewing

  • The Web Conference (WWW)PC Member
    Full Papers2026
  • SIGIRPC Member
    Full Papers2024, 2025Short Papers2023, 2024Resource Papers2025
  • WSDMPC Member
    Research Papers2026Short Papers2026
  • CIKMPC Member
    Full Papers2021, 2023Resource Papers2025Demo Papers2025
  • ECIRPC Member
    Full Papers2021, 2026Short Papers2026Resource Papers2026Workshops2026
  • ICLRPC Member
    Full Papers2025
  • ECMLPC Member
    Full Papers2021
  • CHIIRPC Member
    Full Papers2026Short Papers2026Resource Papers2026Demo Papers2026
  • JCDLPC Member
    Demo Papers2025
  • SIGIR-APPC Member
    Research Papers2024

(Co-)organizer

Sim4IA Workshop @ SIGIR 2024-2025Cognitive-aware user simulation.
IR-RAG Workshop @ SIGIR 2024Personalized and persona-aware RAG systems.
Search Futures Workshop @ ECIR 2025User simulation and generative agents.
Open Search Symposium 2024-2025Open web search and crawling.

At the University of Passau, I am involved in teaching and supporting courses in:

Data Science5779V/5779UE
Web and Data Engineering5430V/5430UE
Machine Learning5729OS
Advanced Topics in Data Science5945UE
SIGIR 2025Excellence in Reviewing

Awarded by ACM SIGIR for excellence in reviewing at SIGIR 2025

ICADL 2024Best Student Full Paper

"Generative Agents Navigating Digital Libraries." International Conference on Asian Digital Libraries. Singapore: Springer Nature Singapore, 2024.

CIKM 2022Best Resource Paper Award

"The SimIIR 2.0 framework: user types, Markov model-based interaction simulation, and advanced query generation." Proceedings of the 31st ACM CIKM, 2022.