SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory

Juntong Wang, Haoyue Zhao, guanghui Pan, Xiyuan Wang, Yanbo Wang, Qiyan Deng, Muhan Zhang

Keywords: Agentic Graph Memory, Structure-Aware Memory, Retrieval-Augmented Generation, Knowledge Graphs, Long-Term Memory

Abstract: Long-term memory is becoming a central bottleneck for language agents. Existing RAG and GraphRAG systems largely treat memory graphs as static retrieval middleware, which limits their ability to recover complete evidence chains from partial cues, exploit reusable graph-structural roles, and improve the memory itself through downstream feedback. We introduce \method{}, a \textbf{S}elf-evolving \textbf{A}gentic \textbf{G}raph-memory \textbf{E}ngine that models graph memory as a dynamic long-term memory substrate. \method{} couples two roles: a memory writer that incrementally constructs structured graph memory from interaction histories, and a Graph Foundation Model-based memory reader to perform retrieval and provide feedback to the memory writer. We provide rigorous theoretical analyses supporting the effectiveness of carefully designed architectural components and the framework. Across multi-hop QA, open-domain retrieval, domain-specific review QA, and long-term agent-memory benchmarks, SAGE improves evidence recovery, answer grounding, and retrieval efficiency: after two self-evolution rounds, it achieves the best average rank on multi-hop QA; in zero-shot open-domain transfer, it reaches 82.5/91.6 Recall@2/5 on NQ. Further results on LongMemEval and HaluMem show that training and reader--writer feedback improve multiple long-term memory and hallucination-diagnostic metrics, suggesting that self-evolving, structure-aware graph memory is a promising foundation for robust long-horizon language agents. Our code is available at https://anonymous.4open.science/r/Unified-Representation-A9D9/

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 8