中文
相关论文

相关论文: Revisiting Observation Reduction for Web Agents: C…

200 篇论文

Accurately predicting end-to-end network latency is essential for enabling reliable task offloading in real-time edge computing applications. This paper introduces a lightweight latency prediction scheme based on rational modelling that…

网络与互联网体系结构 · 计算机科学 2025-11-05 Mohan Liyanage , Eldiyar Zhantileuov , Ali Kadhum Idrees , Rolf Schuster

Users demand fast, seamless webpage experiences, yet developers often struggle to meet these expectations within tight constraints. Performance optimization, while critical, is a time-consuming and often manual process. One of the most…

软件工程 · 计算机科学 2026-01-12 Gideon Peters , SayedHassan Khatoonabadi , Emad Shihab

As LLMs are increasingly deployed as agents, reliable assessment of their agentic capabilities has become essential. However, reported benchmark scores often jointly reflect model capability and the implementation choices each benchmark is…

人工智能 · 计算机科学 2026-05-28 Pengyu Zhu , Lijun Li , Yaxing Lyu , Qianxin Luo , Jingyi Yang , Yi Liu , Tingfeng Hui , Xinyu Yuan , Li Sun , Sen Su , Jing Shao

Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning. However, their increasing autonomy also introduces a new attack surface: adversarial interactions…

人工智能 · 计算机科学 2026-05-05 Sheldon Yu , Yingcheng Sun , Hanqing Guo , Julian McAuley , Qianqian Tong

LLM-based agents have demonstrated strong capabilities in solving complex tasks through multi-step reasoning and tool use. However, existing evaluation protocols primarily focus on task success, overlooking a critical aspect of agent…

人工智能 · 计算机科学 2026-05-29 Minyang Hu , Bo Yang , Zhinuo Zhou , Jiachen Liang , Guo Jiahao , Yiyang Yin , Xiongwei Han

Modern agents powered by thinking LLMs achieve high accuracy through long chain-of-thought reasoning but incur substantial inference costs. While many LLMs now support configurable reasoning levels (e.g., high/medium/low), static strategies…

人工智能 · 计算机科学 2026-03-10 Jingbo Yang , Bairu Hou , Wei Wei , Yujia Bao , Shiyu Chang

We present SLEAN (Simple Lightweight Ensemble Analysis Network), a deterministic framework for coordinating multiple LLM providers through text-based prompt orchestration. Unlike complex multi-agent systems requiring specialized…

软件工程 · 计算机科学 2025-10-14 Matheus J. T. Vargas

Large language models (LLMs) now support extremely long context windows, but the quadratic complexity of vanilla attention results in significantly long Time-to-First-Token (TTFT) latency. Existing approaches to address this complexity…

计算与语言 · 计算机科学 2025-09-04 Qianchao Zhu , Jiangfei Duan , Chang Chen , Siran Liu , Guanyu Feng , Xin Lv , Xiao Chuanfu , Dahua Lin , Chao Yang

We present an autonomous framework that leverages Large Language Models (LLMs) to automate end-to-end business analysis and market report generation. At its core, the system employs specialized agents - Researcher, Reviewer, Writer, and…

计算与语言 · 计算机科学 2025-08-05 Roman Koshkin , Pengyu Dai , Nozomi Fujikawa , Masahito Togami , Marco Visentini-Scarzanella

This paper presents a learning framework to estimate an agent capability and task requirement model for multi-agent task allocation. With a set of team configurations and the corresponding task performances as the training data, linear task…

机器人学 · 计算机科学 2022-11-09 Bo Fu , William Smith , Denise Rizzo , Matthew Castanier , Maani Ghaffari , Kira Barton

Large Language Models can generate synthetic survey responses at low cost, but their accuracy varies unpredictably across questions. We study the design problem of allocating a fixed budget of human respondents across estimation tasks when…

人工智能 · 计算机科学 2026-04-21 Zikun Ye , Hema Yoganarasimhan

Completing paperwork is a challenging and time-consuming problem. Form filling is especially challenging in the pure-image domain without access to OCR, typeset PDF text, or a DOM. For computer agents, it requires multiple abilities,…

人工智能 · 计算机科学 2026-01-23 Matthew Toles , Rattandeep Singh , Isaac Song , Zhou Yu

As users increasingly turn to large language model (LLM) based web agents to automate online tasks, agents may encounter dark patterns: deceptive user interface designs that manipulate users into making unintended decisions. Although dark…

密码学与安全 · 计算机科学 2025-10-22 Devin Ersoy , Brandon Lee , Ananth Shreekumar , Arjun Arunasalam , Muhammad Ibrahim , Antonio Bianchi , Z. Berkay Celik

Large Language Model (LLM)-based multi-agent systems (MAS) are becoming indispensable building blocks for web-scale applications such as web search, social network analytics, and online customer support, where cost-effectiveness is…

人工智能 · 计算机科学 2025-12-15 Shuowei Cai , Yansong Ning , Hao Liu

Multi-agent systems based on large language models (LLMs) for financial trading have grown rapidly since 2023, yet the field lacks a shared framework for understanding what drives performance or for evaluating claims credibly. This survey…

多智能体系统 · 计算机科学 2026-03-31 Phat Nguyen , Thang Pham

Long-horizon agentic search requires iteratively exploring the web over long trajectories and synthesizing information across many sources, and is the foundation for enabling powerful applications like deep research systems. In this work,…

计算与语言 · 计算机科学 2025-10-23 Howard Yen , Ashwin Paranjape , Mengzhou Xia , Thejas Venkatesh , Jack Hessel , Danqi Chen , Yuhao Zhang

The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. While hybrid attention mechanisms combining Full Attention (FA) and Sparse Attention (SA)…

机器学习 · 计算机科学 2026-04-10 Quantong Qiu , Zhiyi Hong , Yi Yang , Haitian Wang , Kebin Liu , Qingqing Dang , Juntao Li , Min Zhang

Modern language agents must operate over long-horizon, multi-turn interactions, where they retrieve external information, adapt to observations, and answer interdependent queries. Yet, most LLM systems rely on full-context prompting,…

计算与语言 · 计算机科学 2025-07-18 Zijian Zhou , Ao Qu , Zhaoxuan Wu , Sunghwan Kim , Alok Prakash , Daniela Rus , Jinhua Zhao , Bryan Kian Hsiang Low , Paul Pu Liang

Large Language Model (LLM)-based agents have emerged as a transformative approach for open-ended problem solving, with information seeking (IS) being a core capability that enables autonomous reasoning and decision-making. While prior…

LLM-based agents represent a paradigm shift in AI, enabling autonomous systems to plan, reason, and use tools while interacting with dynamic environments. This paper provides the first comprehensive survey of evaluation methods for these…

人工智能 · 计算机科学 2026-04-24 Asaf Yehudai , Lilach Eden , Alan Li , Guy Uziel , Yilun Zhao , Roy Bar-Haim , Arman Cohan , Michal Shmueli-Scheuer