Software agents, both human and computational, do not exist in isolation and often need to collaborate or coordinate with others to achieve their goals. In human society, social mechanisms such as norms ensure efficient functioning, and these techniques have been adopted by researchers in multi-agent systems (MAS) to create socially aware agents. However, traditional techniques have limitations, such as operating in limited environments often using brittle symbolic reasoning. The advent of Large Language Models (LLMs) offers a promising solution, providing a rich and expressive vocabulary for norms and enabling norm-capable agents that can perform a range of tasks such as norm discovery, normative reasoning and decision-making. This paper examines the potential of LLM-based agents to acquire normative capabilities, drawing on recent Natural Language Processing (NLP) and LLM research. We present our vision for creating normative LLM agents. In particular, we discuss how the recently proposed "LLM agent" approaches can be extended to implement such normative LLM agents. We also highlight challenges in this emerging field. This paper thus aims to foster collaboration between MAS, NLP and LLM researchers in order to advance the field of normative agents.

翻译：软件代理（包括人类与计算代理）并非孤立存在，它们常需与其它代理协作或协调以实现目标。人类社会通过规范等社会机制保障运行效率，多智能体系统（MAS）研究者已借鉴这些技术构建具有社会感知能力的代理。然而，传统技术存在局限，例如往往在受限环境中采用脆弱的符号推理。大型语言模型（LLM）的出现提供了前景广阔的解决方案，它能为规范提供丰富且富有表现力的词汇，使具备规范能力的代理能够执行规范发现、规范推理和决策制定等任务。本文基于近期自然语言处理（NLP）与LLM研究，探讨基于LLM的代理获取规范能力的潜力，并提出构建规范LLM代理的愿景。我们特别讨论了如何将近期提出的"LLM代理"方法拓展以实现此类规范LLM代理，同时指出了这一新兴领域的挑战。本文旨在促进MAS、NLP与LLM研究者之间的合作，以推动规范代理领域的发展。