发表机构
University of Washington（华盛顿大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究人工智能代理在多智能体世界中的合作问题，借鉴法律制度和契约，通过在时空博弈\CT中研究基于大型语言模型的代理使用不同合同表示，发现自我协商合同可改善合作结果。
AI 中文摘要
随着人工智能代理在多智能体世界中自主运行的增加，它们需要学会与其他代理和人类合作以实现互利。然而，合作具有挑战性，因为合作成本往往在早期产生，而收益在后期才实现，这促使人们产生背叛的动机。人工智能代理如何通过承诺进行合作？在此，我们从人类社会用于解决此类委托代理问题的法律制度和契约中汲取灵感。合同提供了协议的可观察表示，通过条款的执行实现可信承诺。我们在\CT（一种将讨价还价与朝着目标导航相结合的时空博弈）中研究基于大型语言模型的代理使用基于合同的合作的作用。我们研究了一系列合同表示，从编译为代码的正式合同到需要重新解释的自然合同。我们使用不同规模和供应商的一系列大型语言模型主干对代理进行评估。我们发现，自我协商合同可以改善合作结果，超出常规交易的可能性。
英文摘要
As AI agents operate with increasing autonomy in a multi-agent world, they will need to learn to cooperate with other agents and with humans to generate mutual benefits. However, cooperation is a challenge because the costs of cooperation are often incurred early on, but the benefits are only realized later, creating an incentive to defect. How can AI agents cooperate with commitment? Here, we draw on inspiration from legal institutions and contracting that human societies have used to solve principal-agent problems of this kind. Contracts provide observable representations of agreements that enable credible commitments through the enforcement of terms. We study the role of contract-based cooperation using LLM-based agents in \CT, a spatial-temporal game that combines bargaining with navigation towards a goal. We study a suite of contract representations that range from formal contracts that compile to code to natural contracts that require reinterpretation. We evaluate agents with a range of LLM backbones using different sizes and providers. We find that self-negotiated contracts can improve cooperative outcomes beyond what is possible with regular trading.
