AI RESEARCH
Beyond One Path: Evaluating and Enhancing Divergent Thinking in Interactive LLM Agents
arXiv CS.CL
•
ArXi:2605.28465v1 Announce Type: new Divergent thinking is a core dimension of creativity, yet existing evaluations of Large Language Models (LLMs) treat them as single-turn text generations, failing to capture how an agent reasons through iterative interaction. To address this, we