{
  "id": 8822662,
  "title": "What Should We Ask Next? Retrieval-Aware Question Learning under Partial Evidence",
  "url": "https://urgent.news/2026/09/18/what-should-we-ask-next-retrieval-aware-question-learning-under",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-18T15:45:01.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.21924v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Interactive retrieval under partial evidence is a sequential information-acquisition problem: an agent must decide which question will create the most useful evidence for the next retrieval update. Existing systems train this decision by imitating an offline ordering of candidate QA pairs, although question value is determined by the response it elicits and its downstream effect on retrieval. We…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}