paper-with-me

홈 › Papers

Contextual Agentic Memory is a Memo, Not True Memory

2026-04-30 · Binyan Xu, Xilin Dai, Kehuan Zhang arxiv

Current agentic memory systems (vector stores, retrieval-augmented generation, scratchpads, and context-window management) do not implement memory: they implement lookup. We argue that treating lookup as memory is a category error with provable consequences for agent capability, long-term learning, and security. Retrieval generalizes by similarity to stored cases; weight-based memory generalizes by applying abstract rules to inputs never seen before. Conflating the two produces agents that accumulate notes indefinitely without developing expertise, face a provable generalization ceiling on compositionally novel tasks that no increase in context size or retrieval quality can overcome, and are structurally vulnerable to persistent memory poisoning as injected content propagates across all future sessions. Drawing on Complementary Learning Systems theory from neuroscience, we show that biological intelligence solved this problem by pairing fast hippocampal exemplar storage with slow neocortical weight consolidation, and that current AI agents implement only the first half. We formalize these limitations, address four alternative views, and close with a co-existence proposal and a call to action for system builders, benchmark designers, and the memory community.

📄 PDF Abstract BibTeX arXiv:2604.27707

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A-MEM: Agentic Memory for LLM Agents

2025-02-17 · Wujiang Xu, Kai Mei, Hang Gao, Juntao Tan 외

While large language model (LLM) agents can effectively use external tools for complex real-world tasks, they require memory systems to leverage historical experiences. Current memory systems enable basic storage and ret…

Large Language Model

ElephantAgent: Contextual State Continuity in Agentic Systems

2026-07-02 · Jiankai Jin, Xiangzheng Zhang, Zhao Liu, Wenzhuo Xu 외 arxiv

Agentic systems enhance their capabilities by invoking external tools and maintaining persistent memory. However, these external dependencies introduce novel attack surfaces. Recent tool and memory poisoning attacks show…

Evaluating Long-Term Memory for Long-Context Question Answering

2025-10-27 · Alessandra Terranova, Björn Ross, Alexandra Birch arxiv

In order for large language models to achieve true conversational continuity and benefit from experiential learning, they need memory. While research has focused on the development of complex memory systems, it remains u…

Question Answering

RaMem: Contextual Reinstatement for Long-term Agentic Memory

2026-06-22 · Wei Yang, Bryce Kan, Shixuan Li, Li Li 외 arxiv

Long-term memory has become increasingly important for LLM agents that operate across extended interactions and evolving task contexts. Recent memory systems have made past experiences more persistent, compact, and retri…

Oblivion: Self-Adaptive Agentic Memory Control through Decay-Driven Activation

2026-03-31 · Ashish Rana, Chia-Chien Hung, Qumeng Sun, Julian Martin Kunkel 외 arxiv

Human memory adapts through selective forgetting: experiences become less accessible over time but can be reactivated by reinforcement or contextual cues. In contrast, memory-augmented LLM agents rely on "always-on" retr…