中文
相关论文

相关论文: Agent-X: Full Pipeline Acceleration of On-device A…

200 篇论文

Large Language Model (LLM)-based search agents have shown remarkable capabilities in solving complex tasks by dynamically decomposing problems and addressing them through interleaved reasoning and retrieval. However, this interleaved…

人工智能 · 计算机科学 2025-05-20 Tiannuo Yang , Zebin Yao , Bowen Jin , Lixiao Cui , Yusen Li , Gang Wang , Xiaoguang Liu

Personal LLM agents increasingly combine foreground reactive interactions with background proactive monitoring, forming long-lived, stateful LLM flows that interleave prefill and token-by-token decode. While modern heterogeneous SoCs…

分布式、并行与集群计算 · 计算机科学 2026-01-07 Xinming Wei , Jiahao Zhang , Haoran Li , Jiayu Chen , Haoning Guan , Rui Qu , Maoliang Li , Xiang Chen , Guojie Luo

Multimodal large language models (MLLMs) have enabled LLM-based agents to directly interact with application user interfaces (UIs), enhancing agents' performance in complex tasks. However, these agents often suffer from high latency and low…

人工智能 · 计算机科学 2025-05-20 Junting Lu , Zhiyang Zhang , Fangkai Yang , Jue Zhang , Lu Wang , Chao Du , Qingwei Lin , Saravan Rajmohan , Dongmei Zhang , Qi Zhang

Recent advanced LLM-powered agent systems have exhibited their remarkable capabilities in tackling complex, long-horizon tasks. Nevertheless, they still suffer from inherent limitations in resource efficiency, context management, and…

Large Language Models (LLMs) have emerged as powerful tools for accelerating scientific discovery, yet their static knowledge and hallucination issues hinder autonomous research applications. Recent advances integrate LLMs into agentic…

Large Language Models (LLMs), such as OpenAI-o1 and DeepSeek-R1, have demonstrated strong reasoning capabilities. To further enhance LLM capabilities, recent agentic systems, such as Deep Research, incorporate web interactions into LLM…

人工智能 · 计算机科学 2025-10-21 Song Bian , Minghao Yan , Anand Jayarajan , Gennady Pekhimenko , Shivaram Venkataraman

The rapid development of large language model (LLM)-based agents has unlocked new possibilities for autonomous multi-turn reasoning and tool-augmented decision-making. However, their real-world deployment is hindered by severe…

LLM agents have recently emerged as a powerful paradigm for solving complex tasks through planning, tool use, memory retrieval, and multi-step interaction. However, these agentic workflows often introduce substantial input-side overhead,…

计算与语言 · 计算机科学 2026-05-21 Haiquan Lu , Zigeng Chen , Gongfan Fang , Xinyin Ma , Xinchao Wang

Large language models (LLMs) are catalyzing the development of autonomous AI research agents for scientific and engineering discovery. We present FM Agent, a novel and general-purpose multi-agent framework that leverages a synergistic…

Agentic workflows are composed of sequences of interdependent Large Language Model (LLM) calls, and they have become a dominant workload in modern AI systems. These workflows exhibit extensive redundancy from overlapping prompts and…

多智能体系统 · 计算机科学 2026-03-18 Noppanat Wadlom , Junyi Shen , Yao Lu

Recent advancements in Large Language Models (LLMs) have led to the development of intelligent LLM-based agents capable of interacting with graphical user interfaces (GUIs). These agents demonstrate strong reasoning and adaptability,…

人工智能 · 计算机科学 2025-04-16 Wenjia Jiang , Yangyang Zhuang , Chenxi Song , Xu Yang , Joey Tianyi Zhou , Chi Zhang

Language models have shown effectiveness in a variety of software applications, particularly in tasks related to automatic workflow. These models possess the crucial ability to call functions, which is essential in creating AI agents.…

计算与语言 · 计算机科学 2024-04-17 Wei Chen , Zhiyuan Li

Historically, scientific discovery has been a lengthy and costly process, demanding substantial time and resources from initial conception to final results. To accelerate scientific discovery, reduce research costs, and improve research…

Automated machine learning (AutoML) accelerates AI development by automating tasks in the development pipeline, such as optimal model search and hyperparameter tuning. Existing AutoML systems often require technical expertise to set up…

机器学习 · 计算机科学 2025-06-09 Patara Trirat , Wonyong Jeong , Sung Ju Hwang

Current service robots suffer from limited natural language communication abilities, heavy reliance on predefined commands, ongoing human intervention, and, most notably, a lack of proactive collaboration awareness in human-populated…

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

Autonomous agents powered by large language models (LLMs) are increasingly used to automate complex, multi-step tasks such as coding or web-based question answering. While remote, cloud-based agents offer scalability and ease of deployment,…

机器学习 · 计算机科学 2026-05-18 Dzung Pham , Kleomenis Katevas , Ali Shahin Shamsabadi , Hamed Haddadi

The era of the Internet of Agents (IoA) is taking shape: LLM agents are expected to fulfill user goals by orchestrating fast-growing populations of Model Context Protocol (MCP) servers, Agent-to-Agent (A2A) endpoints, reusable skills, and…

人工智能 · 计算机科学 2026-05-29 Wei Zheng , Yang Yan , Yiyang Shao , Jinyang Li , Zeze Chang , Yukuang Jia , Qiming Mao , Chihyung Wang , Jingbin Zhou

Existing AI-generated text detection methods heavily depend on large annotated datasets and external threshold tuning, restricting interpretability, adaptability, and zero-shot effectiveness. To address these limitations, we propose…

计算与语言 · 计算机科学 2025-05-22 Jiatao Li , Mao Ye , Cheng Peng , Xunjian Yin , Xiaojun Wan

The increasing deployment of agentic artificial intelligence (AI) systems has intensified the demand for efficient agent to agent communication, particularly over bandwidth limited wireless links. In embodied AI applications, agents must…

信号处理 · 电气工程与系统科学 2026-04-16 Peiwen Jiang , Yushuo Feng , Jiajia Guo , Chao-Kai Wen , Shi Jin

Agentic LLM applications increasingly execute user requests as multi-step workflows involving planning, tool use, branching, refinement, and synthesis. In such settings, users experience the end-to-end latency of an entire workflow, not the…

分布式、并行与集群计算 · 计算机科学 2026-05-19 You Peng , Youhe Jiang , Wenshuang Li , Xu Xu , Ke Zhou , Jiawei Jiang , Chen Wang , Binhang Yuan
‹ 上一页 1 2 3 10 下一页 ›