paper-with-me

홈 › Papers

All-Mem: Agentic Lifelong Memory via Dynamic Topology Evolution

2026-03-20 · Can Lv, Heng Chang, Shengyu Tao, Mingju Chen, Zhaoxin Fan, Ziwei Zhang, Yuchen Guo, Shiji Zhou arxiv

Lifelong interactive agents are expected to assist users over months or years, which requires continually writing long term memories while retrieving the right evidence for each new query under fixed context and latency budgets. Existing memory systems often degrade as histories grow, yielding redundant, outdated, or noisy retrieved contexts. We present \textbf{All-Mem}, an online/offline lifelong memory framework that maintains a topology structured memory bank via explicit, non destructive consolidation, avoiding the irreversible information loss typical of summarization based compression. In online operation, it anchors retrieval on a bounded visible surface to keep coarse search cost bounded. Periodically offline, an LLM diagnoser proposes confidence scored topology edits executed with gating using three operators: Split, Merge, and Update, while preserving immutable evidence for traceability. At query time, typed links enable hop bounded, budgeted expansion from active anchors to archived evidence when needed. Experiments on \textbf{LoCoMo} and \textbf{LongMemEval-s} show improved retrieval and QA over representative baselines. The code is available at https://github.com/LvCan926/All-Mem.

📄 PDF Abstract BibTeX arXiv:2603.19595

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Governing Evolving Memory in LLM Agents: Risks, Mechanisms, and the Stability and Safety Governed Memory (SSGM) Framework

2026-03-12 · Chingkwun Lam, Jiaxin Li, Lingfei Zhang, Kuo Zhao arxiv

Long-term memory has emerged as a foundational component of autonomous Large Language Model (LLM) agents, enabling continuous adaptation, lifelong multimodal learning, and sophisticated reasoning. However, as memory syst…

AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution

2026-03-01 · Yutao Yang, Junsong Li, Qianjun Pan, Bihao Zhan 외 arxiv

In practical LLM applications, users repeatedly express stable preferences and requirements, such as reducing hallucinations, following institutional writing conventions, or avoiding overly technical wording, yet such in…

LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos

2023-12-07 · Ying Wang, Yanlai Yang, Mengye Ren

In this paper we introduce LifelongMemory, a new framework for accessing long-form egocentric videographic memory through natural language question answering and retrieval. LifelongMemory generates concise video activity…

EgoSchemaFormQuestion AnsweringRetrieval

Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline

2026-03-05 · Guo Chen, Lidong Lu, Yicheng Liu, Liangrui Dong 외 arxiv

While datasets for video understanding have scaled to hour-long durations, they typically consist of densely concatenated clips that differ from natural, unscripted daily life. To bridge this gap, we introduce MM-Lifelon…

A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

2025-08-10 · Jinyuan Fang, Yanwen Peng, Xi Zhang, Yingxu Wang 외 arxiv

Recent advances in large language models have sparked growing interest in AI agents capable of solving complex, real-world tasks. However, most existing agent systems rely on manually crafted configurations that remain s…