Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspective

The paper surveys self‑evolving agents, highlighting that their states—memories, tools, skills, workflows, and inter‑agent relations—are dynamic and can be modeled as evolving graphs. It critiques existing surveys for treating graphs merely as support structures and proposes a framework that views agent evolution as dynamic graph transformation, categorizing methods into node/feature, edge/topology, subgraph activation, and cross‑component co‑evolution. The authors further map dynamic‑graph learning subfields to agent capabilities, discuss potential failure modes, and outline graph‑aware evaluation and governance protocols to guide the design and oversight of self‑evolving agents.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• agents