超越单一路径：评估与增强交互式LLM代理的发散性思维
Beyond One Path: Evaluating and Enhancing Divergent Thinking in Interactive LLM Agents
AI总结：
提出交互式基准MUTATE和策略ReDNA，用于评估和增强LLM代理在路径和动作层面的发散性思维，解决现有框架中即时收敛压力导致的动作固定问题。
摘要：
发散性思维是创造力的核心维度，然而现有对大型语言模型（LLM）的评估将其视为单轮文本生成，未能捕捉代理通过迭代交互进行推理的过程。为解决这一问题，我们引入MUTATE，一个交互式基准，旨在从两个层面评估代理的发散性思维：路径层面，代理发现通向同一目标的多个替代路径；动作层面，单个动作需要非典型、机制转换的物体使用。与仅评估成功不同，MUTATE对完成的路径和偏离路径的尝试都进行评分，捕捉传统成功率忽略的发散性推理。我们对前沿LLM的实验揭示了现有框架中的结构性盲点：当面临即时收敛压力时，它们倾向于陷入即时动作固定，无法改善动作层面的发散性。为克服这一点，我们提出ReDNA，它将无约束的发散候选生成与收敛约束选择分离。ReDNA在两个发散性层面上显著优于先前方法，并能有效泛化到外部创造力环境。我们还确认其成功源于弹性发散推理的定性增强，而非简单的环境探索。
英文摘要：
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, where an agent discovers multiple alternative paths to the same goal, and action-level, where individual actions require non-typical, mechanism-shifting object uses. Unlike success-only evaluations, MUTATE scores both completed paths and off-path attempts, capturing divergent reasoning that conventional success rates discard. Our experiments with frontier LLMs reveal a structural blind spot in existing frameworks: when exposed to immediate convergence pressure, they tend to fall into immediate action fixation, failing to improve action-level divergence. To overcome this, we propose ReDNA, which separates unconstrained divergent candidate generation from convergent constraint selection. ReDNA significantly outperforms prior methods across both divergence levels and generalizes effectively to an external creativity environment. We also confirm its success stems from a qualitative enhancement of resilient divergent reasoning rather than simple environmental exploration.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
