中文
相关论文

相关论文: PISA: A Pragmatic Psych-Inspired Unified Memory Sy…

200 篇论文

Continual learning aims to empower artificial intelligence (AI) with strong adaptability to the real world. For this purpose, a desirable solution should properly balance memory stability with learning plasticity, and acquire sufficient…

机器学习 · 计算机科学 2023-11-10 Liyuan Wang , Xingxing Zhang , Qian Li , Mingtian Zhang , Hang Su , Jun Zhu , Yi Zhong

Organisms constantly pivot between tasks such as evading predators, foraging, traversing rugged terrain, and socializing, often within milliseconds. Remarkably, they preserve knowledge of once-learned environments sans catastrophic…

Memory is critical for enabling large language model (LLM) based agents to maintain coherent behavior over long-horizon interactions. However, existing agent memory systems suffer from two key gaps: they rely on a one-size-fits-all memory…

人工智能 · 计算机科学 2026-02-17 Mingfei Lu , Mengjia Wu , Feng Liu , Jiawei Xu , Weikai Li , Haoyang Wang , Zhengdong Hu , Ying Ding , Yizhou Sun , Jie Lu , Yi Zhang

Memory is fundamental to intelligence, enabling learning, reasoning, and adaptability across biological and artificial systems. While Transformer architectures excel at sequence modeling, they face critical limitations in long-range context…

机器学习 · 计算机科学 2025-08-19 Parsa Omidi , Xingshuai Huang , Axel Laborieux , Bahareh Nikpour , Tianyu Shi , Armaghan Eshaghi

The rapid evolution of Large Language Model (LLM) agents has necessitated robust memory systems to support cohesive long-term interaction and complex reasoning. Benefiting from the strong capabilities of LLMs, recent research focus has…

人工智能 · 计算机科学 2026-04-16 Weiquan Huang , Zixuan Wang , Hehai Lin , Sudong Wang , Bo Xu , Qian Li , Beier Zhu , Linyi Yang , Chengwei Qin

Solving mathematical reasoning problems requires not only accurate access to relevant knowledge but also careful, multi-step thinking. However, current retrieval-augmented models often rely on a single perspective, follow inflexible search…

人工智能 · 计算机科学 2025-11-03 Ali Asgarov , Umid Suleymanov , Aadyant Khatri

A key objective of embodied intelligence is enabling agents to perform long-horizon tasks in dynamic environments while maintaining robust decision-making and adaptability. To achieve this goal, we propose the Spatio-Temporal Memory Agent…

人工智能 · 计算机科学 2025-03-04 Mingcong Lei , Yiming Zhao , Ge Wang , Zhixin Mai , Shuguang Cui , Yatong Han , Jinke Ren

Trustworthy artificial intelligence increasingly relies on probabilistic computation to achieve robustness, interpretability, security and privacy. In practical systems, such workloads interleave deterministic data access with repeated…

机器学习 · 计算机科学 2026-03-27 Xueji Zhao , Likai Pei , Jianbo Liu , Kai Ni , Ningyuan Cao

Deep research agents (DRAs) integrate LLM reasoning with external tools. Memory systems enable DRAs to leverage historical experiences, which are essential for efficient reasoning and autonomous evolution. Existing methods rely on…

人工智能 · 计算机科学 2026-04-21 Jingyang Qiao , Weicheng Meng , Yu Cheng , Zhihang Lin , Zhizhong Zhang , Xin Tan , Jingyu Gong , Kun Shao , Yuan Xie

Experience-driven learning has emerged as a promising paradigm for enabling agents to improve from interaction trajectories by accumulating and reusing past experience. However, existing approaches are predominantly developed in textual…

人工智能 · 计算机科学 2026-05-19 Xingyu Sui , Weixiang Zhao , Yongxin Tang , Yanyan Zhao , Yang Wu , Dandan Tu , Bing Qin

We introduce \prism{} (\textbf{P}robabilistic \textbf{R}etrieval with \textbf{I}nformation-\textbf{S}tratified \textbf{M}emory), an evolutionary memory substrate for multi-agent AI systems engaged in open-ended discovery. \prism{} unifies…

人工智能 · 计算机科学 2026-04-23 Suyash Mishra

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

Memory systems are critical for LLMs, mitigating context window limitations and supporting long-horizon user-LLM interactions. Such systems typically comprise multiple agents responsible for memory construction and retrieval. Existing…

多智能体系统 · 计算机科学 2026-04-28 Wenyu Mao , Haoyang Liu , Haosong Tan , Yaorui Shi , Jiancan Wu , An Zhang , Xiang Wang

Adaptive agent design offers a way to improve human-AI collaboration on time-sensitive tasks in rapidly changing environments. In such cases, to ensure the human maintains an accurate understanding of critical task elements, an assistive…

人工智能 · 计算机科学 2025-10-28 Anwesha Das , John Duff , Jörg Hoffmann , Vera Demberg

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

Autonomous Graphical User Interface (GUI) agents often struggle with multi-step tasks due to constrained context windows and static policies that fail to adapt to dynamic environments. To address these limitations, this work proposes the…

机器学习 · 计算机科学 2026-05-19 Shilong Jin , Lanjun Wang , Zhuosheng Zhang

Real-world artificial intelligence (AI) systems are increasingly required to operate autonomously in dynamic, uncertain, and continuously changing environments. However, most existing AI models rely on predefined objectives, static training…

人工智能 · 计算机科学 2025-11-04 Hong Su

The Human Cognitive Simulation Framework proposes a governed cognitive AI architecture designed to improve personalization, adaptability, and long-term coherence in human AI interaction. The framework integrates short-term memory…

人机交互 · 计算机科学 2026-01-23 Rommel Salas-Guerra

LLM-based agents have been extensively applied across various domains, where memory stands out as one of their most essential capabilities. Previous memory mechanisms of LLM-based agents are manually predefined by human experts, leading to…

机器学习 · 计算机科学 2025-08-26 Zeyu Zhang , Quanyu Dai , Rui Li , Xiaohe Bo , Xu Chen , Zhenhua Dong

Conversational agents struggle to handle long conversations due to context window limitations. Therefore, memory systems are developed to leverage essential historical information. Existing memory systems typically follow a pipeline of…

‹ 上一页 1 2 3 10 下一页 ›