mlsanityData to 7 Oct 2026

CIR at iKAT SCAI 2026: Exploring Clarification Need Prediction in Agentic Conversational Search

arXiv 2607.19801 ↗First posted 22 Jul 2026cs.IRcited by 0

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

This paper presents the participation of the Cologne Information Retrieval group in the iKAT SCAI 2026 shared task. We use an agentic conversational search system, equipped with tools for query rewriting, retrieval and reranking, answer generation, and clarification need prediction and clarification question generation. We experiment with two different neural clarification need prediction models.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 11 of its 20 references that are in the map. First posted on arXiv 22 Jul 2026.

Builds on

11 of 20 references.

Closest ancestors · 1

Same direction, newest first

  1. 2026Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning19 Jan

Other references · 10

  1. 2019Asking Clarifying Questions in Open-Domain Information-Seeking Conversationscited by 136
  2. 2020TREC CAsT 2019: The Conversational Assistance Track Overviewcited by 64
  3. 2021Building and Evaluating Open-Domain Dialogue Corpora with Clarifying Questionscited by 63
  4. 2018Analyzing and Characterizing User Intent in Information-seeking Conversationscited by 36
  5. 2022Conversational Information Seekingcited by 36
  6. 2023Zero-shot Clarifying Question Generation for Conversational Searchcited by 14
  7. 2021Controlling the Risk of Conversational Search via Reinforcement Learningcited by 8
  8. 2024Estimating the Usefulness of Clarifying Questions and Answers for Conversational Searchcited by 4
  9. 2025Zero-Shot and Efficient Clarification Need Prediction in Conversational Searchcited by 4
  10. 2025ChatR1: Reinforcement Learning for Conversational Reasoning and Retrieval Augmented Question Answeringcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024AGENT-CQ: Automatic Generation and Evaluation of Clarifying Questions for Conversational Search with LLMs
  2. 2026Agentic-R: Learning to Retrieve for Agentic Search
  3. 2026RAC: Retrieval-Augmented Clarification for Faithful Conversational Search
  4. 2026From Delivery to Stateful Exploration: Rethinking the Index for Agentic Search
  5. 2026When Your Agent Opens the Chat App: Agent-Controlled Search over Raw Chat Logs Rivals Structured Memory
  6. 2025Self-Taught Agentic Long Context Understanding
  7. 2026When Search Agents Should Ask: DiscoBench for Clarification-Aware Deep Search
  8. 2024STYLE: Improving Domain Transferability of Asking Clarification Questions in Large Language Model Powered Conversational Agents