新闻
UniMem: Complementary Episodic-to-Parametric Memory for Boundary-Agnostic Task Streams
arXiv cs.AI · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- UniMem proposes a self-routing memory framework for LLM agents that balances episodic retrieval and parametric consolidation without explicit task boundaries.
- 为何重要
- Matters for engineers building LLM systems that handle continuous task streams where tasks lack clear boundaries and patterns recur unpredictably.
- 注意
- Paper is recent preprint with no indication of open-source release, code availability, or reproducibility details yet confirmed.
收听本摘要
文章节选
-->
Computer Science > Computation and Language
arXiv:2607.26017v1 (cs)
[Submitted on 28 Jul 2026]
Title: UniMem: Complementary Episodic-to-Parametric Memory for Boundary-Agnostic Task Streams
Authors: Siyu Xia , Chenheng Zhang , Yanting Wu , Haoxuan Li , Jiajun Chai , Xiaohan Wang , Guojun Yin , Wei Lin , Zhouchen Lin , Haifeng Zhang , Jun Wang
View a PDF of the paper titled UniMem: Complementary Episodic-to-Parametric Memory for Boundary-Agnostic Task Streams, by Siyu Xia and 10 other authors
View PDF HTML (experimental)
Abstract: Memory is essential for LLM agents to accumulate task experience and reuse task-specific execution strategies. However, real-world deployment over boundary-agnostic and evolving task streams exposes a fundamental stability-plasticity dilemma. External retrieval-based memory can rapidly absorb new evidence, but it often fails to internalize recurring execution patterns and incurs inference-time retrieval overhead. Parametric memory enables stable and efficient execution once learned, but typically relies on explicit task boundaries and fixed parameter budgets. Inspired by the human brain, which balances plasticity and stability through complementary episodic storage and gradual consolidation, we propose UniMem, a self-routing framework for autonomous memory management. UniMem uses learnable routing tokens as memory controllers, enabling adapt
节选自原文。请前往来源阅读全文。
- agent
- llm
- retrieval
- inference
The Agent Architect
每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。
每周一封邮件,一键退订。您的地址仅用于发送简报。