中文
相关论文

相关论文: MementoGUI: Learning Agentic Multimodal Memory Con…

200 篇论文

Existing Multimodal Large Language Model (MLLM)-based agents face significant challenges in handling complex GUI (Graphical User Interface) interactions on devices. These challenges arise from the dynamic and structured nature of GUI…

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

Graphical User Interface (GUI) agents possess significant commercial and social value, and GUI agents powered by advanced multimodal large language models (MLLMs) have demonstrated remarkable potential. Currently, existing GUI agents…

人工智能 · 计算机科学 2025-09-05 Weizhi Chen , Ziwei Wang , Leyang Yang , Sheng Zhou , Xiaoxuan Tang , Jiajun Bu , Yong Li , Wei Jiang

With the rapid advancements in Large Language Models (LLMs), an increasing number of studies have leveraged LLMs as the cognitive core of agents to address complex task decision-making challenges. Specially, recent research has demonstrated…

多智能体系统 · 计算机科学 2025-03-13 Di Zhao , Longhui Ma , Siwei Wang , Miao Wang , Zhao Lv

Equipping agents with memory is essential for solving real-world long-horizon problems. However, most existing agent memory mechanisms rely on static and hand-crafted workflows. This limits the performance and generalization ability of…

人工智能 · 计算机科学 2026-03-30 Yupeng Huo , Yaxi Lu , Zhong Zhang , Haotian Chen , Yankai Lin

Existing large language model (LLM) based memory systems apply universal, static policies that overlook a fundamental reality: the contexts that are worth storing in memory are different across users. This misalignment wastes limited memory…

人工智能 · 计算机科学 2026-05-26 Yeonjun In , Wonjoong Kim , Sangwu Park , Kanghoon Yoon , Chanyoung Park

Long-horizon LLM agents rely on persistent memory to support interactions across sessions, yet existing memory systems often retrieve context using semantic similarity or broad history inclusion, treating retrieved memories as uniformly…

人工智能 · 计算机科学 2026-05-19 Saksham Sahai Srivastava

Recent advances in AI-assisted programming have empowered agents to execute complex workflows via command-line interfaces, however, existing benchmarks are limited by short task horizons, data contamination from GitHub scraping, and a lack…

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

Nowadays, Large Language Models (LLMs) have been trained using extended context lengths to foster more creative applications. However, long context training poses great challenges considering the constraint of GPU memory. It not only leads…

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…

Recently, there has been a surge of vision-based GUI agents designed to automate everyday mobile and web tasks. These agents interpret raw GUI screenshots and autonomously decide where to click, scroll, or type, which bypasses handcrafted…

机器学习 · 计算机科学 2025-07-09 Yucheng Shi , Wenhao Yu , Zaitang Li , Yonglin Wang , Hongming Zhang , Ninghao Liu , Haitao Mi , Dong Yu

Recent advancements in Large Language Models (LLMs) have improved their ability to process extended conversational contexts, yet fine-tuning and evaluating short- and long-term memories remain difficult due to the absence of datasets that…

计算与语言 · 计算机科学 2026-04-15 Manoj Madushanka Perera , Adnan Mahmood , Kasun Eranda Wijethilake , Quan Z. Sheng

Memory-augmented robotic policies are essential in handling memory-dependent tasks. However, existing approaches typically rely on simple observation window extensions, struggling to simultaneously achieve precise task state tracking and…

机器人学 · 计算机科学 2026-03-20 Liufan Tan , Jiale Li , Gangshan Jing

Recent advances in Multimodal Large Language Models (MLLMs) have enabled the development of mobile agents that can understand visual inputs and follow user instructions, unlocking new possibilities for automating complex tasks on mobile…

机器人学 · 计算机科学 2025-07-24 Ning Li , Xiangmou Qu , Jiamu Zhou , Jun Wang , Muning Wen , Kounianhua Du , Xingyu Lou , Qiuying Peng , Jun Wang , Weinan Zhang

Memory is a fundamental component for enabling long-context LLM agents, supporting persistent state across interactions through a continuous serve-and-update lifecycle. Despite substantial prior work, existing systems suffer from…

数据库 · 计算机科学 2026-05-26 Han Chen , Zining Zhang , Wenqi Pei , Bingsheng He , Ming Wu , Jason Zeng , Michael Heinrich , Wei Wu , Hongbao Zhang

Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution. However, memory is also essential for agents, as it enables them to store, update, and retrieve information over time. This ability…

计算与语言 · 计算机科学 2026-05-19 Yuyao Wang , Zhongjian Zhang , Mo Chi , Kaichi Yu , Yuhan Li , Miao Peng , Bing Tong , Chen Zhang , Yan Zhou , Jia Li

Reusable skills have become a core substrate for improving agent capabilities, yet most existing skill packages encode reusable behavior primarily as textual prompts, executable code, or learned routines. For visual agents, however,…

Modern GUI agents typically rely on a model-centric and step-wise interaction paradigm, where LLMs must re-interpret the UI and re-decide actions at every screen, which is fragile in long-horizon tasks. In this paper, we propose Executable…

人工智能 · 计算机科学 2026-05-13 Zerui Qin , Sheng Yue , Xingyuan Hua , Yongjian Fu , Ju Ren

Existing Graphical User Interface (GUI) agents operate through step-by-step calls to vision language models--taking a screenshot, reasoning about the next action, executing it, then repeating on the new page--resulting in high costs and…