English
Related papers

Related papers: WebWorld: A Large-Scale World Model for Web Agent …

200 papers

The improvement of web agents on current benchmarks raises the question: Do today's agents perform just as well when the web changes? We introduce TimeWarp, a benchmark that emulates the evolving web using containerized environments that…

Artificial Intelligence · Computer Science 2026-03-06 Md Farhan Ishmam , Kenneth Marino

Language agents increasingly require persistent worlds in which they can act, remember, and learn. Existing approaches sit at two extremes: conventional web frameworks provide reliable but fixed contexts backed by databases, while fully…

Artificial Intelligence · Computer Science 2025-12-30 Jichen Feng , Yifan Zhang , Chenggong Zhang , Yifu Lu , Shilong Liu , Mengdi Wang

The paradigm of Large Language Models (LLMs) has increasingly shifted toward agentic applications, where web browsing capabilities are fundamental for retrieving information from diverse online sources. However, existing open-source web…

Computation and Language · Computer Science 2025-09-29 Junteng Liu , Yunji Li , Chi Zhang , Jingyang Li , Aili Chen , Ke Ji , Weiyu Cheng , Zijia Wu , Chengyu Du , Qidi Xu , Jiayuan Song , Zhengmao Zhu , Wenhu Chen , Pengyu Zhao , Junxian He

Digital agents require diverse, large-scale UI trajectories to generalize across real-world tasks, yet collecting such data is prohibitively expensive in both human annotation, infra and engineering perspectives. To this end, we introduce…

Computation and Language · Computer Science 2025-10-17 Yiming Wang , Da Yin , Yuedong Cui , Ruichen Zheng , Zhiqian Li , Zongyu Lin , Di Wu , Xueqing Wu , Chenchen Ye , Yu Zhou , Kai-Wei Chang

The development of autonomous web agents, powered by Large Language Models (LLMs) and reinforcement learning (RL), represents a significant step towards general-purpose AI assistants. However, training these agents is severely hampered by…

Computation and Language · Computer Science 2026-04-21 Hang Ding , Peidong Liu , Junqiao Wang , Ziwei Ji , Meng Cao , Rongzhao Zhang , Lynn Ai , Eric Yang , Tianyu Shi , Lei Yu

While LLM/VLM-powered AI agents have advanced rapidly in math, coding, and computer use, their applications in complex physical and social environments remain challenging. Building agents that can survive and thrive in the real world (for…

Autonomous agents that accomplish complex computer tasks with minimal human interventions have the potential to transform human-computer interaction, significantly enhancing accessibility and productivity. However, existing benchmarks…

Mobile GUI agents powered by large language models have progressed rapidly, creating urgent needs for realistic and comprehensive evaluation. Existing benchmarks prioritize reproducibility but are often limited to open-source apps or…

Artificial Intelligence · Computer Science 2026-05-26 Guohong Liu , Jialei Ye , Pengzhi Gao , Wei Liu , Jian Luan , Yunxin Liu , Yuanchun Li

The web is complex, open-ended, and constantly changing, making it challenging to scale training data for visual web agents. Existing data collection attempts remain limited to offline trajectories for supervised fine-tuning or a handful of…

Artificial Intelligence · Computer Science 2026-05-11 Oğuzhan Fatih Kar , Roman Bachmann , Yuanzheng Gong , Anders Boesen Lindbo Larsen , Afshin Dehghan

We explore building generative neural network models of popular reinforcement learning environments. Our world model can be trained quickly in an unsupervised manner to learn a compressed spatial and temporal representation of the…

Machine Learning · Computer Science 2018-05-10 David Ha , Jürgen Schmidhuber

While GUI agents have shown impressive capabilities in common computer-use tasks such as OSWorld, current benchmarks mainly focus on isolated and single-application tasks. This overlooks a critical real-world requirement of coordinating…

Artificial Intelligence · Computer Science 2026-05-01 Jinchao Li , Yunxin Li , Chenrui Zhao , Zhenran Xu , Baotian Hu , Min Zhang

We introduce WebGames, a comprehensive benchmark suite designed to evaluate general-purpose web-browsing AI agents through a collection of 50+ interactive challenges. These challenges are specifically crafted to be straightforward for…

Machine Learning · Computer Science 2025-02-26 George Thomas , Alex J. Chan , Jikun Kang , Wenqi Wu , Filippos Christianos , Fraser Greenlee , Andy Toulis , Marvin Purtorab

Generative models trained on internet data have revolutionized how text, image, and video content can be created. Perhaps the next milestone for generative models is to simulate realistic experience in response to actions taken by humans,…

Artificial Intelligence · Computer Science 2024-09-27 Sherry Yang , Yilun Du , Kamyar Ghasemipour , Jonathan Tompson , Leslie Kaelbling , Dale Schuurmans , Pieter Abbeel

Learning in environments with large state and action spaces, and sparse rewards, can hinder a Reinforcement Learning (RL) agent's learning through trial-and-error. For instance, following natural language instructions on the Web (such as…

Machine Learning · Computer Science 2018-12-24 Izzeddin Gur , Ulrich Rueckert , Aleksandra Faust , Dilek Hakkani-Tur

Web agents--autonomous systems that navigate and execute tasks on the web on behalf of users--have the potential to transform how people interact with the digital world. However, the most capable web agents today rely on proprietary models…

We introduce WebChain, the largest open-source dataset of human-annotated trajectories on real-world websites, designed to accelerate reproducible research in web agents. It contains 31,725 trajectories and 318k steps, featuring a core…

Artificial Intelligence · Computer Science 2026-04-15 Sicheng Fan , Rui Wan , Yifei Leng , Gaoning Liang , Li Ling , Yanyi Shang , Dehan Kong

Graphical User Interface (GUI) agents show strong capabilities for automating web tasks, but existing interactive benchmarks primarily target benign, predictable consumer environments. Their effectiveness in high-stakes, investigative…

Artificial Intelligence · Computer Science 2026-04-16 Renqi Chen , Zeyin Tao , Jianming Guo , Jing Wang , Zezhou Xu , Jingzhe Zhu , Qingqing Sun , Tianyi Zhang , Shuai Chen

Action-conditioned video prediction models (often referred to as world models) have shown strong potential for robotics applications, but existing approaches are often slow and struggle to capture physically consistent interactions over…

Recent advances in large language model (LLM) have empowered autonomous agents to perform multi-turn interactions with tools and environments. However, scaling such agent training is limited by the lack of diverse and reliable environments.…

Artificial Intelligence · Computer Science 2026-05-26 Zhaoyang Wang , Canwen Xu , Boyi Liu , Yite Wang , Siwei Han , Zhewei Yao , Huaxiu Yao , Yuxiong He

Symbolic world models (e.g., PDDL domains or executable simulators) are central to model-based planning, but training LLMs to generate such world models is limited by the lack of large-scale verifiable supervision. Current approaches rely…

Artificial Intelligence · Computer Science 2025-12-30 Mengkang Hu , Bowei Xia , Yuran Wu , Ailing Yu , Yude Zou , Qiguang Chen , Shijian Wang , Jiarui Jin , Kexin Li , Wenxiang Jiao , Yuan Lu , Ping Luo