中文
相关论文

相关论文: Forgetful but Faithful: A Cognitive Memory Archite…

200 篇论文

For LLM agents, memory management critically impacts efficiency, quality, and security. While much research focuses on retention, selective forgetting--inspired by human cognitive processes (hippocampal indexing/consolidation theory and…

人工智能 · 计算机科学 2026-04-24 Yingjie Gu , Wenjian Xiong , Liqiang Wang , Pengcheng Ren , Chao Li , Xiaojing Zhang , Yijuan Guo , Qi Sun , Jingyao Ma , Shidang Shi

Personalized agents that interact with users over long periods must maintain persistent memory across sessions and update it as circumstances change. However, existing benchmarks predominantly frame long-term memory evaluation as fact…

计算与语言 · 计算机科学 2026-04-23 Md Nayem Uddin , Kumar Shubham , Eduardo Blanco , Chitta Baral , Gengyu Wang

Memory serves as the pivotal nexus bridging past and future, providing both humans and AI systems with invaluable concepts and experience to navigate complex tasks. Recent research on autonomous agents has increasingly focused on designing…

Memory-augmented LLM agents have advanced personalized recommendation, yet existing approaches universally adopt flat memory representations that conflate ephemeral signals with stable preferences, and none provides a complete lifecycle…

计算与语言 · 计算机科学 2026-05-18 Xiang Shen , Yuhang Zhou , Yifan Wu , Zhuokai Zhao , Siyu Lin , Lei Huang , Qianqian Zhong , Lizhu Zhang , Benyu Zhang , Xiangjun Fan , Hong Yan

Long-horizon conversational agents require persistent memory for coherent reasoning, yet uncontrolled accumulation causes temporal decay and false memory propagation. Benchmarks such as LOCOMO and LOCCO report performance degradation from…

人工智能 · 计算机科学 2026-04-03 Payal Fofadiya , Sunil Tiwari

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…

人工智能 · 计算机科学 2025-06-10 Jiazheng Kang , Mingming Ji , Zhe Zhao , Ting Bai

The rapid advancements in artificial intelligence (AI) have primarily focused on the process of learning from data to acquire knowledgeable learning systems. As these systems are increasingly deployed in critical areas, ensuring their…

机器学习 · 计算机科学 2025-12-23 Wei Qian , Chenxu Zhao , Yangyi Li , Mengdi Huai

Large language model (LLM)-powered multi-agent systems (MAS) have demonstrated cognitive and execution capabilities that far exceed those of single LLM agents, yet their capacity for self-evolution remains hampered by underdeveloped memory…

多智能体系统 · 计算机科学 2025-06-17 Guibin Zhang , Muxin Fu , Guancheng Wan , Miao Yu , Kun Wang , Shuicheng Yan

Effective decision-making in the real world depends on memory that is both stable and adaptive: environments change over time, and agents must retain relevant information over long horizons while also updating or overwriting outdated…

机器学习 · 计算机科学 2026-01-22 Oleg Shchendrigin , Egor Cherepanov , Alexey K. Kovalev , Aleksandr I. Panov

The large-scale deployment of personalized healthcare agents demands memory mechanisms that are exceptionally precise, safe, and capable of long-term clinical tracking. However, existing benchmarks primarily focus on daily open-domain…

人工智能 · 计算机科学 2026-05-13 Yihao Wang , Haoran Xu , Renjie Gu , Yixuan Ye , Xinyi Chen , Xinyu Mu , Yuan Gao , Chunxiao Guo , Peng Wei , Jinjie Gu , Huan Li , Ke Chen , Lidan Shou

Existing evaluations of agents with memory typically assess memorization and action in isolation. One class of benchmarks evaluates memorization by testing recall of past conversations or text but fails to capture how memory is used to…

Multi-agent systems built on Large Language Models (LLMs) show exceptional promise for complex collaborative problem-solving, yet they face fundamental challenges stemming from context window limitations that impair memory consistency, role…

人工智能 · 计算机科学 2026-01-13 Sizhe Yuen , Francisco Gomez Medina , Ting Su , Yali Du , Adam J. Sobey

A critical bottleneck in automating AI research is the execution of complex machine learning engineering (MLE) tasks. MLE differs from general software engineering due to computationally expensive evaluation (e.g., model training) and…

人工智能 · 计算机科学 2026-05-21 Jiefeng Chen , Bhavana Dalvi Mishra , Jaehyun Nam , Rui Meng , Tomas Pfister , Jinsung Yoon

Agentic memory is emerging as a key enabler for large language models (LLM) to maintain continuity, personalization, and long-term context in extended user interactions, critical capabilities for deploying LLMs as truly interactive and…

人工智能 · 计算机科学 2025-12-16 Samarth Sarin , Lovepreet Singh , Bhaskarjit Sarmah , Dhagash Mehta

Large language model (LLM)-powered multi-agent systems (MAS) demonstrate remarkable collective intelligence, wherein multi-agent memory serves as a pivotal mechanism for continual adaptation. However, existing multi-agent memory designs…

计算与语言 · 计算机科学 2026-03-10 Muxin Fu , Xiangyuan Xue , Yafu Li , Zefeng He , Siyuan Huang , Xiaoye Qu , Yu Cheng , Yang Yang

Memory systems are fundamental to AI agents, yet existing work often lacks adaptability to diverse tasks and overlooks the constructive and task-oriented role of AI agent memory. Drawing from Piaget's theory of cognitive development, we…

人工智能 · 计算机科学 2025-10-21 Shian Jia , Ziyang Huang , Xinbo Wang , Haofei Zhang , Mingli Song

As generative AI (GenAI) agents become more common in enterprise settings, they introduce security challenges that differ significantly from those posed by traditional systems. These agents are not just LLMs; they reason, remember, and act,…

密码学与安全 · 计算机科学 2025-05-06 Vineeth Sai Narajala , Om Narayan

As sixth-generation (6G) networks move toward ultra-dense, intelligent edge environments, efficient resource management under stringent privacy, mobility, and energy constraints becomes critical. This paper introduces a novel Federated…

机器学习 · 计算机科学 2025-09-15 Francisco Javier Esono Nkulu Andong , Qi Min

Large language models (LLMs) have made significant advances in the field of natural language processing, but they still face challenges such as continuous decision-making, lack of long-term memory, and limited context windows in dynamic…

‹ 上一页 1 2 3 10 下一页 ›