中文
相关论文

相关论文: Long Live the Librarian! A Persistent Search Sub-A…

200 篇论文

While Multi-Agent Systems (MAS) excel at complex tasks, their growing autonomy with operational complexity often leads to critical inefficiencies, such as excessive token consumption and failures arising from misinformation. Existing…

多智能体系统 · 计算机科学 2026-03-03 Fulin Lin , Shaowen Chen , Ruishan Fang , Hongwei Wang , Tao Lin

Recent advancements in Large Language Models (LLMs) and autonomous agents have demonstrated remarkable capabilities across various domains. However, standalone agents frequently encounter limitations when handling complex tasks that demand…

计算与语言 · 计算机科学 2025-05-29 Rennai Qiu , Chen Qian , Ran Li , Yufan Dang , Weize Chen , Cheng Yang , Yingli Zhang , Ye Tian , Xuantang Xiong , Lei Han , Zhiyuan Liu , Maosong Sun

Large Language Model-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in complex tasks. However, manually designing optimal communication topologies is labor-intensive, while automated expansion methods often result…

机器学习 · 计算机科学 2026-05-12 Yulang Chen , Haoxuan Peng , Jinyan Liu , Zichen Wen , Dongrui Liu , Linfeng Zhang

Multi-agent systems (MAS) decompose complex tasks and delegate subtasks to different large language model (LLM) agents and tools. Prior studies have reported the superior accuracy performance of MAS across diverse domains, enabled by…

多智能体系统 · 计算机科学 2025-05-27 Mingyan Gao , Yanzi Li , Banruo Liu , Yifan Yu , Phillip Wang , Ching-Yu Lin , Fan Lai

Multi-agent systems (MAS) based on large language models (LLMs) have demonstrated significant potential in collaborative problem-solving. However, they still face substantial challenges of low communication efficiency and suboptimal task…

计算与语言 · 计算机科学 2025-03-25 Zhexuan Wang , Yutong Wang , Xuebo Liu , Liang Ding , Miao Zhang , Jie Liu , Min Zhang

Complex, non-linear tasks challenge LLM-enhanced multi-agent systems (MAS) due to partial observability and suboptimal coordination. We propose Orchestrator, a novel MAS framework that leverages attention-inspired self-emergent coordination…

多智能体系统 · 计算机科学 2025-09-09 Lukas Beckenbauer , Johannes-Lucas Loewe , Ge Zheng , Alexandra Brintrup

Maintainable and general software allows developers to build robust applications efficiently, yet achieving these qualities often requires refactoring specialized solutions into reusable components. This challenge becomes particularly…

软件工程 · 计算机科学 2025-10-07 Ziga Kovacic , Justin T. Chiu , Celine Lee , Wenting Zhao , Kevin Ellis

Recent work reports strong performance from multi-agent LLM systems (MAS), but these gains are often confounded by increased test-time computation. When computation is normalized, single-agent systems (SAS) can match or outperform MAS, yet…

计算与语言 · 计算机科学 2026-04-14 Dat Tran , Douwe Kiela

Multi-turn agent systems based on Large Language Models (LLMs) have become increasingly popular for software engineering tasks. While LLM agents demonstrate promising effectiveness, the high computational cost of input tokens due to…

软件工程 · 计算机科学 2026-03-17 Yuan-An Xiao , Pengfei Gao , Chao Peng , Yingfei Xiong

Multi-agent systems (MAS) extend large language models (LLMs) from independent single-model reasoning to coordinative system-level intelligence. While existing LLM agents depend on text-based mediation for reasoning and communication, we…

A common method to solve complex problems in software engineering, is to divide the problem into multiple sub-problems. Inspired by this, we propose a Modular Architecture for Software-engineering AI (MASAI) agents, where different…

In this paper, we propose to incorporate the blackboard architecture into LLM multi-agent systems (MASs) so that (1) agents with various roles can share all the information and others' messages during the whole problem-solving process, (2)…

多智能体系统 · 计算机科学 2025-07-03 Bochen Han , Songmao Zhang

Auto-regressive LLM-based software engineering (SWE) agents, henceforth SWE agents, have made tremendous progress (>60% on SWE-Bench Verified) on real-world coding challenges including GitHub issue resolution. SWE agents use a combination…

软件工程 · 计算机科学 2025-04-15 Timothy Bula , Saurabh Pujar , Luca Buratti , Mihaela Bornea , Avirup Sil

LLM-based agents have shown promising capabilities in a growing range of software engineering (SWE) tasks. However, advancing this field faces two critical challenges. First, high-quality training data is scarce, especially data that…

The stringent requirements of mobile edge computing (MEC) applications and functions fathom the high capacity and dense deployment of MEC hosts to the upcoming wireless networks. However, operating such high capacity MEC hosts can…

机器学习 · 计算机科学 2021-02-11 Md. Shirajum Munir , Nguyen H. Tran , Walid Saad , Choong Seon Hong

Large Reasoning Models (LRMs) face two fundamental limitations: excessive token consumption when overanalyzing simple information processing tasks, and inability to access up-to-date knowledge beyond their training data. We introduce MARS…

Library reuse is a widely adopted practice in software development, however, re-used libraries are not always up-to-date, thus including unnecessary bugs or vulnerabilities. Brutely upgrading libraries to the latest versions is not feasible…

软件工程 · 计算机科学 2025-04-03 Rui Lu

Software engineers operating in complex and dynamic environments must continuously adapt to evolving requirements, learn iteratively from experience, and reconsider their approaches based on new insights. However, current large language…

人工智能 · 计算机科学 2025-04-03 Antonis Antoniades , Albert Örwall , Kexun Zhang , Yuxi Xie , Anirudh Goyal , William Wang

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

We develop Latent Exploration Score (LES) to mitigate over-exploration in Latent Space Optimization (LSO), a popular method for solving black-box discrete optimization problems. LSO utilizes continuous optimization within the latent space…

机器学习 · 计算机科学 2025-02-25 Omer Ronen , Ahmed Imtiaz Humayun , Richard Baraniuk , Randall Balestriero , Bin Yu
‹ 上一页 1 2 3 10 下一页 ›