About
The First Workshop on AutoResearch for Information Retrieval and Recommender Systems (AutoR²) will be held as a half-day workshop at the 20th ACM International Conference on Web Search and Data Mining (WSDM 2027) in Hong Kong, China, on February 19, 2027.
Venue: Cordis, Hong Kong, 555 Shanghai Street, Mong Kok, Hong Kong.
AutoR² will bring together researchers and practitioners from IR, RS, automated machine learning, AI agents, self-evolving systems, AI for Science, and industrial machine learning systems to establish a shared foundation and research agenda for AutoResearch. Through AutoR², we aim to (i) bring together academic and industrial researchers to develop a shared understanding of the scope, capabilities, and limitations of AutoResearch for IR & RS; (ii) provide a forum for presenting and debating new methodologies, research agents, infrastructure, benchmarks, evaluation protocols, and industrial experiences; and (iii) identify key challenges and future directions for reliable and effective research automation in IR & RS. Expected outcomes include a clearer conceptualization of AutoResearch for IR & RS, a shared set of open research challenges, stronger connections between academic and industrial efforts, and a community for continued discussion on research automation in IR & RS.
You can expect a half-day program featuring keynote talks, paper presentations with dedicated discussion time, and an interactive roundtable on open research questions and future directions. Please note that AutoR² is an in-person workshop, and accepted papers will be presented onsite.
Topics of Interest
We welcome submissions on, but not limited to, the following themes:
1 Concept and Applicability of AutoResearch for IR/RS
- Concept and boundaries of AutoResearch for IR/RS
- Suitable retrieval, ranking, and recommendation problems
- Academic and industrial AutoResearch settings
2 AutoResearch Methodology for IR/RS
- Research planning and decision-making for multi-stage IR/RS systems
- Learning from IR/RS research experience and system evolution
- Human roles in offline and online research loops
3 AutoResearch-Driven IR/RS Development
- Data, feature, and representation development
- Model architecture, objectives, and training optimization
- Retrieval, ranking, recommendation, and system-level optimization
- Research-to-deployment and online strategy iteration
4 Infrastructure for AutoResearch in IR/RS
- Benchmarks and executable IR/RS research environments
- Offline and online validation environments
- Safe access to data, compute, and production systems
5 Evaluation of AutoResearch for IR/RS
- Evaluation of generated IR/RS methods and findings
- Evaluation of AutoResearch capabilities and efficiency
- Engineering and scientific value in IR/RS
6 Lessons from IR/RS AutoResearch for Automated Scientific Discovery
- IR/RS as a computational testbed for AutoResearch
- From offline–online feedback to scientific validation loops
- Research experience and continual scientific improvement
See the Call for Papers for submission details.
Important Dates
All deadlines are at 23:59 Anywhere on Earth (AoE).
| Paper submission deadline | 30 November 2026 |
|---|---|
| Paper notification | 18 December 2026 |
| Camera-ready | To be announced |
| Workshop day | 19 February 2027 |
Keynote Speakers
More speakers to be announced. Talk titles, abstracts, and speaker bios will be posted on the Keynotes page.
