AI RESEARCH

InfoGatherer: Principled Information Seeking via Evidence Retrieval and Strategic Questioning

arXiv CS.CL

ArXi:2603.05909v1 Announce Type: new LLMs are increasingly deployed in high-stakes domains such as medical triage and legal assistance, often as document-grounded QA systems in which a user provides a description, relevant sources are retrieved, and an LLM generates a prediction. In practice, initial user queries are often underspecified, and a single retrieval pass is insufficient for reliable decision-making, leading to incorrect and overly confident answers.