跳到正文
arXiv cs.MA· Wenhao Yuan, Longhui Yuan, Zexi Jia, Ningzhe Shi, Jingwei Li, Shipeng Cen, Pengcheng Luo, Jie Zhou, Jinchao Zhang·· 23 小时前AI 评分40

OpenKAGE:通过知识共享的智能体群体演化实现开放世界开放式终身学习

OpenKAGE: Open-Ended Lifelong Learning in the Open World via Knowledge-Sharing Agent-Group Evolution

AI 导读

OpenKAGE 是一个面向开放式终身学习的智能体群体演化框架,让智能体在开放世界中自主探索,并通过积累和复用自身交互与他人经验持续获得新能力。它采用双层知识表示(情景记忆层与可迁移经验技能层),并将文本经验语义整合为持续演化的共享知识图谱、可执行技能原样共享。

正文 · 原文

View PDF HTML (experimental)

Abstract:Building autonomous agents that continually explore open worlds and acquire new capabilities through experience is a long-standing aspiration in artificial intelligence. Existing research often pursues lifelong learning within predefined tasks, curricula, or objectives, with self-improvement largely confined to individual agents. We introduce OpenKAGE, an agent-group evolution framework for open-ended lifelong learning. Within this framework, agents autonomously explore open worlds and continually acquire new capabilities by accumulating and reusing knowledge from their own interactions and the experience of others. OpenKAGE builds on two key mechanisms: (1) a two-layer knowledge representation, with a memory layer for situated memories and an experience layer for transferable experience and skills that retains the applicability conditions needed for reuse; and (2) a knowledge-sharing mechanism that semantically consolidates textual experience into a continuously evolving shared knowledge graph, while executable skills are shared verbatim. In Minecraft, OpenKAGE supports open-ended lifelong learning, enabling agent groups to sustain exploration and reach advanced technological milestones. Furthermore, the accumulated knowledge can be transferred to a newly initialized agent group on a different backbone model, improving its survival and exploration progress.
Subjects: Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)
Cite as: arXiv:2611.24302 [cs.AI]
  (or arXiv:2611.24302v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.24302

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Wenhao Yuan [view email]
[v1] Wed, 18 Nov 2026 12:11:56 UTC (1,984 KB)

来源:arXiv cs.MA · arxiv.org