English
Related papers

Related papers: GTA: Generating Long-Horizon Tasks for Web Agents …

200 papers

Most commodity software lacks accessible Application Programming Interfaces (APIs), requiring autonomous agents to interact solely through pixel-based Graphical User Interfaces (GUIs). In this API-free setting, large language model…

Artificial Intelligence · Computer Science 2026-03-26 Chenwei Tang , Lin Long , Xinyu Liu , Jingyu Xing , Zizhou Wang , Joey Tianyi Zhou , Jiawei Du , Liangli Zhen , Jiancheng Lv

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…

Artificial Intelligence · Computer Science 2025-09-05 Weizhi Chen , Ziwei Wang , Leyang Yang , Sheng Zhou , Xiaoxuan Tang , Jiajun Bu , Yong Li , Wei Jiang

Long-horizon large language model (LLM) agents are fundamentally limited by context. As interactions become longer, tool descriptions, retrieved memories, and raw environmental feedback accumulate and push out the information needed for…

Pre-trained large language models (LLMs) have recently achieved better generalization and sample efficiency in autonomous web automation. However, the performance on real-world websites has still suffered from (1) open domainness, (2)…

Machine Learning · Computer Science 2024-02-27 Izzeddin Gur , Hiroki Furuta , Austin Huang , Mustafa Safdari , Yutaka Matsuo , Douglas Eck , Aleksandra Faust

The rapid development of large language and multimodal models has sparked significant interest in using proprietary models, such as GPT-4o, to develop autonomous agents capable of handling real-world scenarios like web navigation. Although…

Computation and Language · Computer Science 2024-10-28 Hongliang He , Wenlin Yao , Kaixin Ma , Wenhao Yu , Hongming Zhang , Tianqing Fang , Zhenzhong Lan , Dong Yu

Test-time scaling has become a standard way to improve performance and boost reliability of neural network models. However, its behavior on agentic, multi-step tasks remains less well-understood: small per-step errors can compound over long…

Artificial Intelligence · Computer Science 2026-02-13 Nicholas Lee , Lutfi Eren Erdogan , Chris Joseph John , Surya Krishnapillai , Michael W. Mahoney , Kurt Keutzer , Amir Gholami

Designing and evaluating personalized and proactive assistant agents remains challenging due to the time, cost, and ethical concerns associated with human-in-the-loop experimentation. Existing Human-Computer Interaction (HCI) methods often…

Human-Computer Interaction · Computer Science 2025-11-25 Ziyi Xuan , Yiwen Wu , Xuhai Xu , Vinod Namboodiri , Mooi Choo Chuah , Yu Yang

Web scraping is a powerful technique that extracts data from websites, enabling automated data collection, enhancing data analysis capabilities, and minimizing manual data entry efforts. Existing methods, wrappers-based methods suffer from…

Computation and Language · Computer Science 2024-09-27 Wenhao Huang , Zhouhong Gu , Chenghao Peng , Zhixu Li , Jiaqing Liang , Yanghua Xiao , Liqian Wen , Zulong Chen

We introduce DABstep, a novel benchmark for evaluating AI agents on realistic multi-step data analysis tasks. DABstep comprises over 450 real-world challenges derived from a financial analytics platform, requiring models to combine…

Machine Learning · Computer Science 2025-07-01 Alex Egg , Martin Iglesias Goyanes , Friso Kingma , Andreu Mora , Leandro von Werra , Thomas Wolf

Long-horizon, repetitive workflows are common in professional settings, such as processing expense reports from receipts and entering student grades from exam papers. These tasks are often tedious for humans since they can extend to extreme…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Jing Wu , Daphne Barretto , Yiye Chen , Nicholas Gydé , Yanan Jian , Yuhang He , Vibhav Vineet

Algorithm audits have increased in recent years due to a growing need to independently assess the performance of automatically curated services that process, filter, and rank the large and dynamic amount of information available on the…

Computers and Society · Computer Science 2023-04-06 Roberto Ulloa , Mykola Makhortykh , Aleksandra Urman

In automated web testing, generating test scripts from natural language task descriptions is crucial for enhancing the test generation process. This activity involves creating the correct sequences of actions to form test scripts for future…

Software Engineering · Computer Science 2025-09-12 Duy Cao , Phu Nguyen , Vy Le , Tien N. Nguyen , Vu Nguyen

Recent progress in GUI agents has substantially improved visual grounding, yet robust planning remains challenging, particularly when the environment deviates from a canonical initial state. In real applications, users often invoke…

Artificial Intelligence · Computer Science 2026-05-26 Henry Hengyuan Zhao , Kaiming Yang , Wendi Yu , Difei Gao , Mike Zheng Shou

For web agents to be practically useful, they must adapt to the continuously evolving web environment characterized by frequent updates to user interfaces and content. However, most existing benchmarks only capture the static aspects of the…

Computation and Language · Computer Science 2024-07-17 Yichen Pan , Dehan Kong , Sida Zhou , Cheng Cui , Yifei Leng , Bing Jiang , Hangyu Liu , Yanyi Shang , Shuyan Zhou , Tongshuang Wu , Zhengyang Wu

Recent advancements in multi-agent systems have demonstrated significant potential for enhancing creative task performance, such as long video generation. This study introduces three innovations to improve multi-agent collaboration. First,…

Multiagent Systems · Computer Science 2025-10-28 Zheng Wei , Mingchen Li , Zeqian Zhang , Ruibin Yuan , Pan Hui , Huamin Qu , James Evans , Maneesh Agrawala , Anyi Rao

Real-world data is represented in both structured (e.g., graph connections) and unstructured (e.g., textual, visual information) formats, encompassing complex relationships that include explicit links (such as social connections and user…

Artificial Intelligence · Computer Science 2024-12-24 Yuhao Yang , Jiabin Tang , Lianghao Xia , Xingchen Zou , Yuxuan Liang , Chao Huang

Large Language Models (LLMs) have significantly advanced tool-augmented agents, enabling autonomous reasoning via API interactions. However, executing multi-step tasks within massive tool libraries remains challenging due to two critical…

Artificial Intelligence · Computer Science 2026-04-15 Rongzhe Wei , Ge Shi , Min Cheng , Na Zhang , Pan Li , Sarthak Ghosh , Vaibhav Gorde , Leman Akoglu

Current LLM agent benchmarks, which predominantly focus on binary pass/fail tasks such as code generation or search-based question answering, often neglect the value of real-world engineering that is often captured through the iterative…

Learning to solve long horizon temporally extended tasks with reinforcement learning has been a challenge for several years now. We believe that it is important to leverage both the hierarchical structure of complex tasks and to use expert…

Machine Learning · Computer Science 2022-10-18 Bharat Prakash , Nicholas Waytowich , Tim Oates , Tinoosh Mohsenin

Long-horizon workflow agents that operate effectively over extended periods are essential for truly autonomous systems. Their reliable execution critically depends on the ability to reason through ambiguous situations in which clarification…

Computation and Language · Computer Science 2026-03-23 George Pu , Michael S. Lee , Udari Madhushani Sehwag , David J. Lee , Bryan Zhu , Yash Maurya , Mohit Raghavendra , Yuan Xue , Samuel Marc Denton