NomicLaw：大语言模型在协作立法中涌现的信任与策略性论证
NomicLaw: Emergent Trust and Strategic Argumentation in LLMs During Collaborative Law-Making
AI总结：
本文提出NomicLaw多智能体模拟框架，研究LLM在协作立法中的信任、互惠与策略性论证行为，实验显示智能体自发结盟、背叛并调整言辞影响决策，揭示其社交推理与说服潜力。
摘要：
近年来，大语言模型（LLMs）的进步已将其能力从基础文本处理扩展到复杂推理任务，包括法律解释、论证和策略性互动。然而，对LLM在开放式多智能体环境中行为（尤其是涉及法律和伦理困境审议的环境）的实证理解仍然有限。我们提出了NomicLaw，一个结构化的多智能体模拟框架，其中LLM参与协作立法，通过提出规则、为其辩护并对同行提案进行投票来回应复杂的法律情境。我们通过投票模式定量衡量信任与互惠性，并定性评估智能体如何使用策略性语言来论证提案并影响结果。涉及同质与异质LLM群体的实验表明，智能体自发形成联盟、背叛信任并调整其言辞以塑造集体决策。我们的结果凸显了十个开源LLM潜在的社交推理与说服能力，并为未来能够自主谈判、协调及起草法律文本的AI系统设计提供了见解。
英文摘要：
Recent advancements in large language models (LLMs) have extended their capabilities from basic text processing to complex reasoning tasks, including legal interpretation, argumentation, and strategic interaction. However, empirical understanding of LLM behavior in open-ended, multi-agent settings especially those involving deliberation over legal and ethical dilemmas remains limited. We introduce NomicLaw, a structured multi-agent simulation where LLMs engage in collaborative law-making, responding to complex legal vignettes by proposing rules, justifying them, and voting on peer proposals. We quantitatively measure trust and reciprocity via voting patterns and qualitatively assess how agents use strategic language to justify proposals and influence outcomes. Experiments involving homogeneous and heterogeneous LLM groups demonstrate how agents spontaneously form alliances, betray trust, and adapt their rhetoric to shape collective decisions. Our results highlight the latent social reasoning and persuasive capabilities of ten open-source LLMs and provide insights into the design of future AI systems capable of autonomous negotiation, coordination and drafting legislation in legal settings.
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。
