Skip to content

[论文讨论] Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory #61

@gqy20

Description

@gqy20

论文信息

标题: Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory
作者: Haozhen Zhang, Haodong Yue, Tao Feng, Quanyu Long, Jianzhu Bao 等 11 位作者
发布时间: 2026-02-05
分类: cs.AI
PDF: Download

简介

Memory is increasingly central to Large Language Model (LLM) agents operating beyond a single context window, yet most existing systems rely on offline, query-agnostic memory construction that can be inefficient and may discard query-critical information. Although runtime memory utilization is a natural alternative, prior work often incurs substantial overhead and offers limited explicit control over the performance-cost trade-off. In this work, we present \textbf{BudgetMem}, a runtime agent memory framework for explicit, query-aware performance-cost control. BudgetMem structures memory processing as a set of memory modules, each offered in three budget tiers (i.e., \textsc{Low}/\textsc{Mid}/\textsc{High}). A lightweight router performs budget-tier routing across modules to balance task performance and memory construction cost, which is implemented as a compact neural policy trained with reinforcement learning. Using BudgetMem as a unified testbed, we study three complementary strategies for realizing budget tiers: implementation (method complexity), reasoning (inference behavior), and capacity (module model size). Across LoCoMo, LongMemEval, and HotpotQA, BudgetMem surpasses strong baselines when performance is prioritized (i.e., high-budget setting), and delivers better accuracy-cost frontiers under tighter budgets...

推荐理由

推荐论文1:BudgetMem解决了LLM Agent内存管理的核心痛点,框架设计完整,实验覆盖三个基准测试,具有实际应用价值

讨论

请对这篇论文发表您的见解:

  • 论文的创新点是什么?
  • 方法是否合理?
  • 实验结果是否可信?
  • 有哪些可以改进的地方?

由 arXiv Monitor 自动创建

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions