Beyond One Path: Evaluating and Enhancing Divergent Thinking in Interactive LLM Agents 事件

Beyond One Path: Evaluating and Enhancing Divergent Thinking in Interactive LLM Agents arXiv:2605.28465v1 Announce Type: new Abstract: 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 introduce MUTATE, an interactive benchmark designed to evaluate agentic divergent thinking at two levels: path-level,