语言模型、智能体模型与世界模型：面向机器推理与规划的 LAW
Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planning
AI总结：
本文提出 LAW 视角，将语言模型、智能体模型与世界模型结合，以语言模型为后端，增强机器在多场景中的稳健推理与规划能力。
摘要：
尽管大语言模型在许多应用中取得了巨大成功，但由于其推理、学习和建模能力的固有局限，它们在各类（语言、具身和社会）场景中往往难以进行一致的推理与规划。在这篇立场论文中，我们提出了一种机器推理的新视角 LAW，它将 Language models（语言模型）、Agent models（智能体模型）和 World models（世界模型）的概念联系起来，以实现更稳健、更通用的推理能力。具体而言，我们认为世界模型和智能体模型是更好的推理抽象，它引入了审慎的类人推理的关键要素，包括关于世界和其他智能体的信念、对后果的预期、目标/奖励以及战略规划。关键在于，LAW 中的语言模型充当实现该系统或其要素的后端，从而提供计算能力和适应性。我们回顾了取得相关进展的近期研究，并讨论了将 LAW 框架落地的未来研究方向。
英文摘要：
Despite their tremendous success in many applications, large language models often fall short of consistent reasoning and planning in various (language, embodied, and social) scenarios, due to inherent limitations in their inference, learning, and modeling capabilities. In this position paper, we present a new perspective of machine reasoning, LAW, that connects the concepts of Language models, Agent models, and World models, for more robust and versatile reasoning capabilities. In particular, we propose that world and agent models are a better abstraction of reasoning, that introduces the crucial elements of deliberate human-like reasoning, including beliefs about the world and other agents, anticipation of consequences, goals/rewards, and strategic planning. Crucially, language models in LAW serve as a backend to implement the system or its elements and hence provide the computational power and adaptability. We review the recent studies that have made relevant progress and discuss future research directions towards operationalizing the LAW framework.
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。
