Cologne Information Retrieval group presents agentic conversational search system

Researchers from the Cologne Information Retrieval group have developed an agentic conversational search system for the iKAT SCAI 2026 shared task. This system incorporates tools for query rewriting, retrieval, reranking, and answer generation. A key focus of their work is on clarification need prediction and the generation of clarification questions, with experiments conducted on two distinct neural models for this purpose. AI

IMPACT This research contributes to improving conversational search systems by focusing on how agents can better understand user needs and ask clarifying questions.

RANK_REASON The item is an academic paper detailing research on conversational search systems and clarification need prediction. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.IR (Information Retrieval) →

• alphaXiv
• answer generation
• CatalyzeX Code Finder for Papers
• clarification need prediction
• clarification question generation
• Cologne Information Retrieval group
• Connected Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• iKAT SCAI 2026
• Influence Flower
• Litmaps
• neural clarification need prediction models
• query rewrite
• reranking
• retrieval
• ScienceCast
• scite Smart Citations

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →