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

TL;DR

SAGE introduces a dynamic, self-evolving graph memory system for language agents that enhances evidence recovery, answer grounding, and retrieval efficiency through structured, feedback-driven memory updates.

Contribution

It presents a novel self-evolving graph memory framework that couples incremental memory construction with feedback-based retrieval, improving long-term memory performance.

Findings

Achieves best average rank on multi-hop QA after two self-evolution rounds.

Reaches 82.5/91.6 Recall@2/5 on NQ in zero-shot open-domain transfer.

Training and feedback improve long-term memory and reduce hallucinations.

Abstract

Long-term memory is becoming a central bottleneck for language agents. Exsting 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-structrual roles, and improve the memory itself through downstream feedback. We introduce SAGE, a Self-evolving Agentic Graph-memory Engine that models graph memory as a dynamic long-term memory substrate. SAGE couples two roles: a memory writer that incrementally constucts 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 rigorooous theoretical annalyses supporting the framework. Across multi-hop QA, open-domain retireval, 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 traning 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.