让大模型像人一样自主规划日常活动，靠内在欲望驱动。
Simulating Human-like Daily Activities with Desire-driven Autonomy
- 用动态价值系统模拟人类多维欲望，驱动任务自主生成
- 在文本模拟器中生成连贯、多样的日常行为，符合人类表现
- 适合研究自主智能体与人性行为模拟的学者
欲望驱使人类自主与复杂世界互动。当前人工智能代理需依赖显式指令或奖励函数，限制了其自主性与行为多样性。本文提出欲望驱动的自主代理（D2A），使大型语言模型（LLM）能基于内在多维度欲望，自主提出并选择任务。D2A的动机框架基于需求理论构建，包含社交互动、自我实现与自我照顾等人类特质欲望。每一步，代理评估当前状态价值，生成候选活动，并选择最契合内在动机的行动。我们在Concordia——一个文本模拟器——上进行实验，结果表明，该代理能生成连贯且情境相关的日常活动，表现出类人行为的变异性与适应性。与其它基于LLM的代理对比，本方法显著提升了模拟活动的合理性。
原文摘要 · Abstract (English)
Desires motivate humans to interact autonomously with the complex world. In contrast, current AI agents require explicit task specifications, such as instructions or reward functions, which constrain their autonomy and behavioral diversity. In this paper, we introduce a Desire-driven Autonomous Agent (D2A) that can enable a large language model (LLM) to autonomously propose and select tasks, motivated by satisfying its multi-dimensional desires. Specifically, the motivational framework of D2A is mainly constructed by a dynamic Value System, inspired by the Theory of Needs. It incorporates an understanding of human-like desires, such as the need for social interaction, personal fulfillment, and self-care. At each step, the agent evaluates the value of its current state, proposes a set of candidate activities, and selects the one that best aligns with its intrinsic motivations. We conduct experiments on Concordia, a text-based simulator, to demonstrate that our agent generates coherent, contextually relevant daily activities while exhibiting variability and adaptability similar to human behavior. A comparative analysis with other LLM-based agents demonstrates that our approach significantly enhances the rationality of the simulated activities.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。