发表机构
NextGen PlatformAI C Corp.（下一代平台人工智能C公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究大型语言模型智能体进步引发的问题，提出受治理多智能体架构实现递归式自我提升，以个人奇点为目标，详细介绍智能体各要素及架构组成，形式化多种机制并提供设计与路线图。
AI 中文摘要
大型语言模型智能体在规划、使用工具、维护记忆和执行长期任务方面不断进步，引发两个相关问题：智能体如何改进学习和行动机制，以及这种改进如何提升用户而非软件本身的持久能力。本文提出一种用于递归式自我提升智能体的受治理多智能体架构，并引入个人奇点作为有限的人类-人工智能共同发展目标。每个智能体由目标契约、有限范围、经过验证的工具注册表、工具级测试、端到端基准、所有者控制的自主策略、路由策略、记忆和改进策略定义。超出范围的任务转移给其他可问责智能体或新创建的利基智能体。用户面临的自动索引选择交互式、混合式、自主式或预定操作而不超越外部权限。该架构结合了快速规划器-执行器-验证器循环、较慢的证据门控改进循环、外部治理平面、分散的智能体谱系、所有者主导的智能体铸造厂以及协调工作、计算成像、过程学习和个人学习智能体的个人奇点操作系统。我们形式化了范围、路由、改进接受、有限目标进化、工具优先执行和人类能力转移，并提供安全不变量、基准设计和实施路线图。这是一篇立场和系统设计论文,并非无限制递归自我提升或个人奇点已实现的证据。
英文摘要
Large language model (LLM) agents can plan, use tools, maintain memory, and execute long-horizon tasks. This paper proposes Self-Aware Recursively Self-Improving (SARSI) agents: governed agents that maintain a persistent self-model of identity, goals, capabilities, limitations, uncertainty, relationships, history, and developmental change, and use that model to guide and evaluate recursive improvement. Self-awareness is defined functionally and does not imply subjective experience or phenomenal consciousness. We pair SARSI agents with personal singularity, a bounded human-AI co-development objective in which an agent ecosystem helps a user approach an expanding, user-defined feasible capability frontier. Each agent has a goal contract, bounded scope, validated tool registry, tool tests, end-to-end benchmarks, owner-controlled autonomy, routing, memory, self-model, and improvement policy. A scope router assigns every accepted task to one accountable primary agent and transfers out-of-scope work through structured handoffs. A user-facing Auto-Index selects interactive, hybrid, autonomous, or scheduled behavior without overriding external permissions. The architecture combines a planner-executor-verifier loop, an evidence-gated improvement loop, an external governance plane, decentralized lineages, an owner-directed agent foundry, and a Personal Singularity OS coordinating working, computational-imaging, work-process-learning, and personal-learning agents. We formalize functional self-awareness, scope, routing, improvement acceptance, bounded goal evolution, tool-first execution, and human capability transfer, and provide safety invariants, benchmark design, and a staged implementation roadmap. This is a position and systems-design paper, not evidence that consciousness, unrestricted recursive self-improvement, or personal singularity has been achieved.
Comments28 pages, 5 figures, 7 tables, and 5 algorithms. Position and systems-design paper
