智能体
arxiv.org ·
SAGE：面向结构感知联想记忆的自演化智能体图记忆引擎
该论文提出 SAGE，将图记忆建模为动态长期记忆基底，而非静态检索中间件。系统包含两个角色：memory writer 从交互历史增量构建结构化图记忆，基于 Graph Foundation Model 的 memory reader 执行检索并向 writer 提供反馈，从而让记忆随下游反馈自我改进。作者称在多跳 QA、开放域检索、领域评审 QA 与长期智能体记忆基准上改善了证据恢复、答案落地与检索效率；两轮自演化后多跳 QA 平均排名最优，零样本开放域迁移在 NQ 上达到 Recall@2/5 为 82.5/91.6，并在 LongMemEval 与 HaluMem 上报告长期记忆与幻觉诊断指标的提升。
AI推荐理由 arXiv 预印本，作者与摘要信息完整，属可验证的研究首发（v1 2026-05-12，v2 2026-09-22）。核心新信息是把图记忆从静态检索中间件改为可自演化的长期记忆基底：memory writer 增量构建结构化图记忆，基于 Graph Foundation Model 的 memory reader 负责检索并向 writer 反馈，形成读写闭环。摘要给出多跳 QA、开放域检索、领域评审 QA、LongMemEval、HaluMem 等基准上的提升，并称两轮自演化后多跳 QA 平均排名最佳、NQ 零样本迁移 Recall@2/5 达 82.5/91.6。局限：仅有摘要级证据，未提供具体基线、消融与统计细节，理论分析结论无法从片段核实，指标为作者自报。
78
正文
Computer Science > Artificial Intelligence
arXiv:2605.12061 (cs)
[Submitted on 12 May 2026 (v1), last revised 22 Sep 2026 (this version, v2)]
Title:SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory
Authors:Juntong Wang, Haoyue Zhao, guanghui Pan, Xiyuan Wang, Yanbo Wang, Qiyan Deng, Muhan Zhang
View a PDF of the paper titled SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory, by Juntong Wang and 6 other authors
View PDF
HTML (experimental)
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.
Subjects:
Artificial Intelligence (cs.AI)
Cite as:
arXiv:2605.12061 [cs.AI]
(or
arXiv:2605.12061v2 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2605.12061
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Juntong Wang [view email]
[v1]
Tue, 12 May 2026 12:47:43 UTC (8,595 KB)
[v2]
Tue, 22 Sep 2026 12:34:27 UTC (8,640 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory, by Juntong Wang and 6 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-05
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)