English
Related papers

Related papers: Storage Is Not Memory: A Retrieval-Centered Archit…

200 papers

Long-term memory is crucial for agents in specialized web environments, where success depends on recalling interface affordances, state dynamics, workflows, and recurring failure modes. However, existing memory benchmarks for agents mostly…

Computation and Language · Computer Science 2026-05-13 Di Wu , Zixiang Ji , Asmi Kawatkar , Bryan Kwan , Jia-Chen Gu , Nanyun Peng , Kai-Wei Chang

Every major benchmark for LLM memory systems, LoCoMo foremost, measures whether a model answered correctly, not whether the memory system retrieved correctly. A system returning its entire belief store achieves recall of 1.0 and passes…

Information Retrieval · Computer Science 2026-05-28 Jeffrey Flynt

Driven by the development of persistent, self-adapting autonomous agents, equipping these systems with high-fidelity memory access for long-horizon reasoning has emerged as a critical requirement. However, prevalent retrieval-based memory…

Artificial Intelligence · Computer Science 2026-03-20 Zhixing You , Jiachen Yuan , Jason Cai

Large Language Models (LLMs) face a crucial challenge from fixed context windows and inadequate memory management, leading to a severe shortage of long-term memory capabilities and limited personalization in the interactive experience with…

Artificial Intelligence · Computer Science 2025-06-10 Jiazheng Kang , Mingming Ji , Zhe Zhao , Ting Bai

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…

Artificial Intelligence · Computer Science 2026-05-01 Binyan Xu , Xilin Dai , Kehuan Zhang

Procedural memory enables large language model (LLM) agents to internalize "how-to" knowledge, theoretically reducing redundant trial-and-error. However, existing frameworks predominantly suffer from a "passive accumulation" paradigm,…

Artificial Intelligence · Computer Science 2026-04-16 Zouying Cao , Jiaji Deng , Li Yu , Weikang Zhou , Zhaoyang Liu , Bolin Ding , Hai Zhao

Memory management is vital for LLM agents to handle long-term interaction and personalization. Most research focuses on how to organize and use memory summary, but often overlooks the initial memory extraction stage. In this paper, we argue…

Computation and Language · Computer Science 2026-01-09 Chengyuan Yang , Zequn Sun , Wei Wei , Wei Hu

Providing AI agents with reliable long-term memory that does not hallucinate remains an open problem. Current approaches to memory for LLM agents -- sliding windows, summarization, embedding-based RAG, and flat fact extraction -- each…

Computation and Language · Computer Science 2026-04-14 Artem Gadzhiev , Andrew Kislov

Large Language Model (LLM) agents require persistent memory to maintain personalization, factual continuity, and long-horizon reasoning, yet standard context-window and retrieval-augmented generation (RAG) pipelines degrade over…

Artificial Intelligence · Computer Science 2026-04-07 Shu Wang , Edwin Yu , Oscar Love , Tom Zhang , Tom Wong , Steve Scargall , Charles Fan

To enable reliable long-term interaction, LLM agents require a memory system that can faithfully store, efficiently retrieve, and deeply reason over accumulated dialogue history. Most existing methods adopt an extracted fact based paradigm:…

Computation and Language · Computer Science 2026-05-20 Jingwei Sun , Jianing Zhu , Jiangchao Yao , Tongliang Liu , Bo Han

AI coding agents operate in a paradox: they possess vast parametric knowledge yet cannot remember a conversation from an hour ago. Existing memory systems store text in vector databases with single-channel retrieval, require cloud LLMs for…

Artificial Intelligence · Computer Science 2026-04-07 Varun Pratap Bhardwaj

Long-term memory is fundamental for personalized and autonomous agents, yet populating it remains a bottleneck. Existing systems treat memory extraction as a one-shot, passive transcription from context to structured entries, which…

Computation and Language · Computer Science 2026-04-13 Jingyi Kang , Chunyu Li , Ding Chen , Bo Tang , Feiyu Xiong , Zhiyu Li

Agentic AI require persistent memory to store user-specific histories beyond the limited context window of LLMs. Existing memory systems use dense vector databases or knowledge-graph traversal (or hybrid), incurring high retrieval latency…

Artificial Intelligence · Computer Science 2026-02-17 Yi Li , Lianjie Cao , Faraz Ahmed , Puneet Sharma , Bingzhe Li

Memory is critical for LLM-based agents to preserve past observations for future decision-making, where factual memory serves as its foundational part. However, existing approaches to constructing factual memory face several limitations.…

Artificial Intelligence · Computer Science 2026-03-18 Zeyu Zhang , Rui Li , Xiaoyan Zhao , Yang Zhang , Wenjie Wang , Xu Chen , Tat-Seng Chua

Memory data are ubiquitous in Large Language Model (LLM)-based agents (e.g., OpenClaw and Manus). A few recent works have attempted to exploit agents'memory for improving their performance on the question-answering (QA) task, but they lack…

Computation and Language · Computer Science 2026-05-18 Jiawei Yu , Yixiang Fang , Xilin Liu , Yuchi Ma

Large Language Model (LLM) has exhibited strong reasoning ability in text-based contexts across various domains, yet the limitation of context window poses challenges for the model on long-range inference tasks and necessitates a memory…

Information Retrieval · Computer Science 2026-03-11 Mengwei Yuan , Jianan Liu , Jing Yang , Xianyou Li , Weiran Yan , Yichao Wu , Penghao Liang

Long conversations with an AI agent create a simple problem for one user: the history is useful, but carrying it verbatim is expensive. We study personalized agent memory: one user's conversation history with an agent, distilled into a…

Artificial Intelligence · Computer Science 2026-03-16 Sydney Lewis

Existing memory systems for language agents address memory management: how to retrieve and page more information within a context budget. We address a complementary problem -- memory utility: what experience is worth keeping, and how it…

Artificial Intelligence · Computer Science 2026-03-18 James Rhodes , George Kang

Large language models still struggle with reliable long-term conversational memory: simply enlarging context windows or applying naive retrieval often introduces noise and destabilizes responses. We present APEX-MEM, a conversational memory…

Computation and Language · Computer Science 2026-04-17 Pratyay Banerjee , Masud Moshtaghi , Shivashankar Subramanian , Amita Misra , Ankit Chadha

Long-term memory is one of the key factors influencing the reasoning capabilities of Large Language Model Agents (LLM Agents). Incorporating a memory mechanism that effectively integrates past interactions can significantly enhance…

Computation and Language · Computer Science 2025-08-01 Haoran Sun , Shaoning Zeng