人类启发的智能体复杂度对LLM驱动策略推理者的影响
The Influence of Human-inspired Agentic Sophistication in LLM-driven Strategic Reasoners
AI总结：
本研究通过三种智能体设计在猜测游戏中与人类对比，发现人类启发的认知结构能提升LLM智能体与人类策略行为的一致性，但复杂度与人类相似度呈非线性关系。
摘要：
大型语言模型（LLM）的迅速崛起已将人工智能（AI）研究转向智能体系统，促使采用更弱且更灵活的智能体概念。然而，这一转变引发了关于基于LLM的智能体在多大程度上复制人类策略推理的关键问题，尤其是在博弈论情境中。在此背景下，我们通过评估三种智能体设计来考察智能体复杂度在塑造人工推理者表现中的作用：一个简单的博弈论模型、一个非结构化的LLM即智能体模型，以及一个集成到传统智能体框架中的LLM。以猜测游戏为测试平台，我们将这些智能体与人类参与者在一般推理模式和基于角色的个体目标方面进行了基准比较。此外，我们引入了混淆游戏场景，以评估智能体在训练分布之外进行泛化的能力。我们的分析涵盖了25种智能体配置中的2000多个推理样本，结果表明，人类启发的认知结构可以增强LLM智能体与人类策略行为的一致性。然而，智能体设计复杂度与人类相似度之间的关系是非线性的，凸显了对底层LLM能力的关键依赖，并暗示了简单架构增强的局限性。
英文摘要：
The rapid rise of large language models (LLMs) has shifted artificial intelligence (AI) research toward agentic systems, motivating the use of weaker and more flexible notions of agency. However, this shift raises key questions about the extent to which LLM-based agents replicate human strategic reasoning, particularly in game-theoretic settings. In this context, we examine the role of agentic sophistication in shaping artificial reasoners' performance by evaluating three agent designs: a simple game-theoretic model, an unstructured LLM-as-agent model, and an LLM integrated into a traditional agentic framework. Using guessing games as a testbed, we benchmarked these agents against human participants across general reasoning patterns and individual role-based objectives. Furthermore, we introduced obfuscated game scenarios to assess agents' ability to generalise beyond training distributions. Our analysis, covering over 2000 reasoning samples across 25 agent configurations, shows that human-inspired cognitive structures can enhance LLM agents' alignment with human strategic behaviour. Still, the relationship between agentic design complexity and human-likeness is non-linear, highlighting a critical dependence on underlying LLM capabilities and suggesting limits to simple architectural augmentation.
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。
