Agent Memory Research in 2026: A Data-Driven Survey and Extended Taxonomy
T. Weiß
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
Agent memory has emerged as a first-class primitive in the pursuit of intelligent, long-horizon AI agents. The original survey by Liu et al. established a unified 3x3x3 taxonomy—Forms x Functions x Dynamics—organizing roughly 200 papers up to January 2026. Since then, the field has continued to accelerate: we catalogue 220 papers (as of June 2026), including 21 works published between February and June 2026 that reveal cross-cutting themes the original taxonomy was not designed to capture. In this paper we make three contributions. First, we describe a fully data-driven methodology for curating and maintaining a living paper survey, with a single-source-of-truth YAML file, automated validation pipelines, and an open-source infrastructure. Second, we extend the original taxonomy with three novel orthogonal dimensions—Temporal Dynamics, Modality, and Biological Inspiration—that capture the emerging themes of forgetting curves, multimodal memory, and neurocognitively inspired architectures. Third, we conduct a gap analysis that identifies underpopulated taxonomy cells, missing evaluation standards, and a concrete research roadmap spanning short, medium, and long-term milestones. All data, code, and a browsable web interface accompany this paper.
逐年被引趋势
暂无年度引用数据
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
计算机 / AIAI-based Problem Solving and Planning
Psychiatry, Mental Health, Neuroscience · Reinforcement Learning in Robotics