UniMem: Complementary Episodic-to-Parametric Memory for Boundary-Agnostic Task Streams

-->

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

…