AI RESEARCH
Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People
arXiv CS.AI
•
ArXi:2510.20886v2 Announce Type: replace-cross Many emerging applications of AI--from scientific discovery to medical diagnosis--require agents to seek information strategically: forming hypotheses, asking targeted questions, and making decisions under uncertainty. In high-stakes settings with limited resources, do language models (LMs) behave like rational agents? Drawing on insights from human cognition, we develop methods to evaluate and enhance agentic information-seeking. First, we