中文
相关论文

相关论文: Agent.xpu: Efficient Scheduling of Agentic LLM Wor…

200 篇论文

Accelerator-based heterogeneous architectures, such as CPU-GPU, CPU-TPU, and CPU-FPGA systems, are widely adopted to support the popular artificial intelligence (AI) algorithms that demand intensive computation. When deployed in real-time…

分布式、并行与集群计算 · 计算机科学 2025-05-20 An Zou , Yuankai Xu , Yinchen Ni , Jintao Chen , Yehan Ma , Jing Li , Christopher Gill , Xuan Zhang , Yier Jin

Edge intelligence delivers low-latency inference, yet most edge analytics remain hard-coded and must be redeployed as conditions change. When data patterns shift or new questions arise, engineers often need to write new scripts and push…

分布式、并行与集群计算 · 计算机科学 2026-04-14 Chinmaya Kumar Dehury , Siddharth Singh Kushwaha , Qiyang Zhang , Alaa Saleh , Praveen Kumar Donta

Hybrid parallelism techniques are essential for efficiently training large language models (LLMs). Nevertheless, current automatic parallel planning frameworks often overlook the simultaneous consideration of node heterogeneity and dynamic…

分布式、并行与集群计算 · 计算机科学 2025-06-04 Ruilong Wu , Xinjiao Li , Yisu Wang , Xinyu Chen , Dirk Kutscher

We present Comp-X, the first intelligently interactive image compression paradigm empowered by the impressive reasoning capability of large language model (LLM) agent. Notably, commonly used image codecs usually suffer from limited coding…

计算机视觉与模式识别 · 计算机科学 2025-08-22 Yixin Gao , Xin Li , Xiaohan Pan , Runsen Feng , Bingchen Li , Yunpeng Qi , Yiting Lu , Zhengxue Cheng , Zhibo Chen , Jörn Ostermann

LLM agents in markets present algorithmic collusion risks. While prior work shows LLM agents reach supracompetitive prices through tacit coordination, existing research focuses on hand-crafted prompts. The emerging paradigm of prompt…

人工智能 · 计算机科学 2026-04-21 Yingtao Tian

Foundation models have become central to unifying perception and planning in robotics, yet real-world deployment exposes a mismatch between their monolithic assumption that a single model can handle all cognitive functions and the…

机器人学 · 计算机科学 2025-12-02 Nan Sun , Bo Mao , Yongchang Li , Chenxu Wang , Di Guo , Huaping Liu

Large Language Models (LLMs) are rapidly being integrated into real-world applications, yet their autoregressive architectures introduce significant inference time variability, especially when deployed across heterogeneous edge-cloud…

分布式、并行与集群计算 · 计算机科学 2025-12-30 Panlong Wu , Yifei Zhong , Danyang Chen , Ting Wang , Fangxin Wang

The past two years have witnessed the evolution of large language model (LLM)-based multi-agent systems from labor-intensive manual design to partial automation (\textit{e.g.}, prompt engineering, communication topology) and eventually to…

机器学习 · 计算机科学 2025-02-12 Guibin Zhang , Kaijie Chen , Guancheng Wan , Heng Chang , Hong Cheng , Kun Wang , Shuyue Hu , Lei Bai

AI agents are increasingly deployed in complex, interactive environments, yet their runtime remains a major bottleneck for training, evaluation, and real-world use. Typical agent behavior unfolds sequentially, with each action requiring an…

人工智能 · 计算机科学 2026-04-24 Naimeng Ye , Arnav Ahuja , Georgios Liargkovas , Yunan Lu , Kostis Kaffes , Tianyi Peng

Security Operations Centers (SOCs) are overwhelmed by tens of thousands of daily alerts, with only a small fraction corresponding to genuine attacks. This overload creates alert fatigue, leading to overlooked threats and analyst burnout.…

计算与语言 · 计算机科学 2025-10-02 Bowen Wei , Yuan Shen Tay , Howard Liu , Jinhao Pan , Kun Luo , Ziwei Zhu , Chris Jordan

Automatically generating agentic workflows -- executable operator graphs or codes that orchestrate reasoning, verification, and repair -- has become a practical way to solve complex tasks beyond what single-pass LLM generation can reliably…

多智能体系统 · 计算机科学 2026-02-12 Jialiang Wang , Shengxiang Xu , Hanmo Liu , Jiachuan Wang , Yuyu Luo , Shimin Di , Min-Ling Zhang , Lei Chen

Large language models (LLMs) have demonstrated exceptional proficiency in understanding and generating human language, but efficient inference on resource-constrained embedded devices remains challenging due to large model sizes and…

硬件体系结构 · 计算机科学 2025-07-15 Weihong Xu , Haein Choi , Po-kai Hsu , Shimeng Yu , Tajana Rosing

With the growing adoption of Large Language Models (LLMs) in automating complex, multi-agent workflows, organizations face mounting risks from errors, emergent behaviors, and systemic failures that current evaluation methods fail to…

人工智能 · 计算机科学 2025-09-19 NVJK Kartik , Garvit Sapra , Rishav Hada , Nikhil Pareek

Recent advances in Large Language Models (LLMs) have propelled intelligent agents from reactive responses to proactive support. While promising, existing proactive agents either rely exclusively on observations from enclosed environments…

Modern scientific discovery increasingly relies on high-performance computing for complex modeling and simulation. A key challenge in improving parallel program performance is efficiently mapping tasks to processors and data to memory, a…

机器学习 · 计算机科学 2025-06-02 Anjiang Wei , Allen Nie , Thiago S. F. X. Teixeira , Rohan Yadav , Wonchan Lee , Ke Wang , Alex Aiken

From ancient water wheels to robotic process automation (RPA), automation technology has evolved throughout history to liberate human beings from arduous tasks. Yet, RPA struggles with tasks needing human-like intelligence, especially in…

机器人学 · 计算机科学 2023-11-27 Yining Ye , Xin Cong , Shizuo Tian , Jiannan Cao , Hao Wang , Yujia Qin , Yaxi Lu , Heyang Yu , Huadong Wang , Yankai Lin , Zhiyuan Liu , Maosong Sun

The convergence of artificial intelligence and materials science presents a transformative opportunity, but achieving true acceleration in discovery requires moving beyond task-isolated, fine-tuned models toward agentic systems that plan,…

The growing complexity of power system operations has created an urgent need for intelligent, automated tools to support reliable and efficient grid management. Conventional analysis tools often require significant domain expertise and…

系统与控制 · 电气工程与系统科学 2025-12-25 Yihan , Wen , Xin Chen

LLM-based multi-agent systems (MAS) have emerged as a promising approach to tackle complex tasks that are difficult for individual LLMs. A natural strategy is to scale performance by increasing the number of agents; however, we find that…

人工智能 · 计算机科学 2026-02-04 Yingxuan Yang , Chengrui Qu , Muning Wen , Laixi Shi , Ying Wen , Weinan Zhang , Adam Wierman , Shangding Gu

Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digital workflows. However, real-world execution environments are far from ideal: pop-ups,…

人工智能 · 计算机科学 2026-05-26 Jingwei Sun , Jianing Zhu , Yuanyi Li , Tongliang Liu , Xia HU , Bo Han