让AI像人一样在真实世界中好奇探索，边学边用。
Artificial Agency Program: Curiosity, compression, and communication in agents
- 用好奇心驱动学习，约束资源做选择性观察与行动
- 在有限预算下优化感知、决策与执行的平衡
- 适合研究具身智能、自主系统与人机协作的学者
本文提出人工代理计划（AAP），主张将人工智能视为嵌入现实、受资源限制的代理系统，其发展由好奇心驱动的学习进展所推动。核心观点是：当AI作为扩展的人-工具系统一部分时最有效，能提升感知、理解与行动能力，并降低人、工具与环境之间的交互摩擦。该计划整合预测压缩、内在动机、赋能与控制、界面质量（统一）以及语言/自我通信，将其作为选择性信息瓶颈。通过明确成本、分阶段实验和多模态标记化测试平台，实现代理在观测、行动与思辨之间分配有限预算。目标是建立连接内在动机、信息论、热力学、有限理性与现代推理系统的概念与实验框架。
原文摘要 · Abstract (English)
This paper presents the Artificial Agency Program (AAP), a position and research agenda for building AI systems as reality embedded, resource-bounded agents whose development is driven by curiosity-as-learning-progress under physical and computational constraints. The central thesis is that AI is most useful when treated as part of an extended human--tool system that increases sensing, understanding, and actuation capability while reducing friction at the interface between people, tools, and environments. The agenda unifies predictive compression, intrinsic motivation, empowerment and control, interface quality (unification), and language/self-communication as selective information bottlenecks. We formulate these ideas as a falsifiable program with explicit costs, staged experiments, and a concrete multimodal tokenized testbed in which an agent allocates limited budget among observation, action, and deliberation. The aim is to provide a conceptual and experimental framework that connects intrinsic motivation, information theory, thermodynamics, bounded rationality, and modern reasoning systems
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。