Back to AI News
arxiv

OpenKAGE: Open-Ended Lifelong Learning via Knowledge-Sharing Agent Groups

OpenKAGE is an agent-group evolution framework for open-ended lifelong learning in which agents autonomously explore open worlds and acquire new capabilities by accumulating and reusing knowledge from their own interactions and those of others. It combines a two-layer knowledge representation, separating situated memories from transferable experience and skills with their applicability conditions, with a knowledge-sharing mechanism that consolidates textual experience into an evolving shared knowledge graph while sharing executable skills verbatim. In Minecraft, the framework supports sustained exploration and lets agent groups reach advanced technological milestones, and the accumulated knowledge transfers to a newly initialized agent group on a different backbone model, improving survival and exploration progress.

AI Brief

It proposes a concrete mechanism for multi-agent knowledge sharing and transfer in open-ended lifelong learning, with demonstrated cross-backbone transfer in Minecraft.

arXiv:2611.24302v1 Announce Type: new 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.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!