MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs

Excerpt

arXiv:2605.10064v2 Announce Type: replace Abstract: Self-evolving language-model agents must decide what to learn next and how to preserve what they have learned across iterations. Existing systems typically carry this cross-iteration knowledge as natural-language feedback, flat episodic memory, or implicit reinforcement signals, none of which cleanly supports a frozen weak backbone at inference time. This paper introduces MAGE (Multi-Agent Graph-guided Evolution), a framework that externalizes