UniMem: Complementary Episodic-to-Parametric Memory for Boundary-Agnostic Task Streams
- ID: ad70b784
- arXiv: https://arxiv.org/abs/2607.26017
- PDF: https://arxiv.org/pdf/2607.26017
- 作者: Siyu Xia, Chenheng Zhang, Yanting Wu, Haoxuan Li, Jiajun Chai, Xiaohan Wang, Guojun Yin, Wei Lin, Zhouchen Lin, Haifeng Zhang, Jun Wang
- 发布: 2026-07-28
- arXiv 分类: cs.CL
- 抓取时间: 2026-07-30
中文导读
UniMem 用可学习的 routing token 做 memory controller，新/稀疏任务进 episodic buffer 走检索，反复出现的可靠模式 consolidate 进可扩展 parametric memory，无需任务标签也能按需扩展记忆。在长程流式任务序列上平均 +4.0 EM，三个 backbone 一致。解决 retrieval-based memory（快但浅）和 parametric memory（稳但依赖任务边界）之间的 stability-plasticity 矛盾。
为什么值得关注
Agent 记忆自动内外化路由：routing token 让新任务走检索、反复模式进参数记忆
English 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 adaptive coordination between complementary memory pathways: novel or sparse tasks are retained in an episodic buffer for retrieval-augmented execution, while recurring and reliable patterns are consolidated into expandable parametric memory. By decoupling task identification from task execution with routing tokens and parametric memory blocks, UniMem expands memory on demand without task labels during deployment or uncontrolled parameter growth. Experiments on long-horizon streaming task sequences show that UniMem consistently outperforms baselines while maintaining execution fidelity, achieving an average gain of 4.0 EM points across three backbone models.