当信任碰撞：通过囚徒困境解码人类与LLM的合作动态
When Trust Collides: Decoding Human-LLM Cooperation Dynamics through the Prisoner's Dilemma
AI总结：
本研究通过30名参与者与不同声明身份的智能体进行重复囚徒困境游戏，揭示了智能体身份和性别对人类合作行为及决策延迟的显著影响，强调了智能体框架在塑造有效且伦理的人机交互中的重要性。
摘要：
随着大型语言模型（LLMs）日益具备自主决策能力，它们为混合动机情境下的人机合作引入了新的挑战与机遇。尽管先前研究主要在辅助或合作角色中考察AI，但人类如何与被视为独立且具战略性的AI智能体互动却鲜为人知。本研究通过让30名参与者（15名男性，15名女性）与在声明身份上不同的智能体进行重复囚徒困境游戏，调查了人类对LLM智能体的合作态度与行为，这些身份包括： purported human（据称的人类）、rule-based AI（基于规则的AI）和LLM agent（LLM智能体）。分析了包括合作率、决策延迟、主动合作行为和信任恢复容忍度在内的行为指标，以评估智能体身份和参与者性别的影响。结果显示，声明的智能体身份对大多数合作相关行为有显著影响，同时在决策延迟上存在显著的性别差异。此外，定性回应表明，这些行为差异受参与者对智能体的解读和期望所影响。这些发现有助于我们理解人类在与自主智能体竞争性合作中的适应，并强调了智能体框架在塑造有效且伦理的人机交互中的重要性。
英文摘要：
As large language models (LLMs) become increasingly capable of autonomous decision-making, they introduce new challenges and opportunities for human-AI cooperation in mixed-motive contexts. While prior research has primarily examined AI in assistive or cooperative roles, little is known about how humans interact with AI agents perceived as independent and strategic actors. This study investigates human cooperative attitudes and behaviors toward LLM agents by engaging 30 participants (15 males, 15 females) in repeated Prisoner's Dilemma games with agents differing in declared identity: purported human, rule-based AI, and LLM agent. Behavioral metrics, including cooperation rate, decision latency, unsolicited cooperative acts and trust restoration tolerance, were analyzed to assess the influence of agent identity and participant gender. Results revealed significant effects of declared agent identity on most cooperation-related behaviors, along with notable gender differences in decision latency. Furthermore, qualitative responses suggest that these behavioral differences were shaped by participants interpretations and expectations of the agents. These findings contribute to our understanding of human adaptation in competitive cooperation with autonomous agents and underscore the importance of agent framing in shaping effective and ethical human-AI interaction.
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。
