English
Related papers

Related papers: WebShop: Towards Scalable Real-World Web Interacti…

200 papers

Graphical User Interface (GUI) agents can automate complex tasks across digital environments, but their development is hindered by the scarcity of high-quality trajectory data for training. Existing approaches rely on expensive human…

Computation and Language · Computer Science 2025-03-04 Yiheng Xu , Dunjie Lu , Zhennan Shen , Junli Wang , Zekun Wang , Yuchen Mao , Caiming Xiong , Tao Yu

Autonomous agents that execute human tasks by controlling computers can enhance human productivity and application accessibility. However, progress in this field will be driven by realistic and reproducible benchmarks. We present…

Training models to act as agents that can effectively navigate and perform actions in a complex environment, such as a web browser, has typically been challenging due to lack of training data. Large language models (LLMs) have recently…

This paper provides a roadmap that explores the question of how to imbue learning agents with the ability to understand and generate contextually relevant natural language in service of achieving a goal. We hypothesize that two key…

Artificial Intelligence · Computer Science 2021-03-19 Prithviraj Ammanabrolu , Mark O. Riedl

We present an optimised multi-modal dialogue agent for interactive learning of visually grounded word meanings from a human tutor, trained on real human-human tutoring data. Within a life-long interactive learning period, the agent, trained…

Computation and Language · Computer Science 2017-10-02 Yanchao Yu , Arash Eshghi , Oliver Lemon

Large language model-based web agents have demonstrated strong performance on realistic web interaction tasks. However, existing evaluations are predominantly conducted under relatively stable and well-behaved interaction conditions, which…

Software Engineering · Computer Science 2026-04-21 Haoyue Bai , Dong Wang , Long Chen , Bingguang Hao , Pengyang Shao , Yonghui Yang , Yicheng He , Chenyi Zhuang

We introduce REAL, a benchmark and framework for multi-turn agent evaluations on deterministic simulations of real-world websites. REAL comprises high-fidelity, deterministic replicas of 11 widely-used websites across domains such as…

LLMs have recently demonstrated strong potential in simulating online shopper behavior. Prior work has improved action prediction by applying SFT on action traces with LLM-generated rationales, and by leveraging RL to further enhance…

Computers and Society · Computer Science 2025-10-23 Yimeng Zhang , Jiri Gesi , Ran Xue , Tian Wang , Ziyi Wang , Yuxuan Lu , Sinong Zhan , Huimin Zeng , Qingjun Cui , Yufan Guo , Jing Huang , Mubarak Shah , Dakuo Wang

People rely heavily on context to enrich meaning beyond what is literally said, enabling concise but effective communication. To interact successfully and naturally with people, user-facing artificial intelligence systems will require…

Computation and Language · Computer Science 2023-11-23 Daniel Fried , Nicholas Tomlin , Jennifer Hu , Roma Patel , Aida Nematzadeh

Modern Large Language Model (LLM) agents promise end to end assistance with real-world software tasks, yet existing benchmarks evaluate LLM agents almost exclusively in pre-baked environments where every dependency is pre-installed. To fill…

Software Engineering · Computer Science 2025-07-15 Avi Arora , Jinu Jang , Roshanak Zilouchian Moghaddam

From professional research to everyday planning, many tasks are bottlenecked by wide-scale information seeking, which is more repetitive than cognitively complex. With the rapid development of Large Language Models (LLMs), automated search…

Computation and Language · Computer Science 2025-08-29 Ryan Wong , Jiawei Wang , Junjie Zhao , Li Chen , Yan Gao , Long Zhang , Xuan Zhou , Zuo Wang , Kai Xiang , Ge Zhang , Wenhao Huang , Yang Wang , Ke Wang

Language agents have demonstrated remarkable potential in web search and information retrieval. However, these search agents assume user queries are complete and unambiguous, an assumption that diverges from reality where users begin with…

A/B testing experiment is a widely adopted method for evaluating UI/UX design decisions in modern web applications. Yet, traditional A/B testing remains constrained by its dependence on the large-scale and live traffic of human…

Human-Computer Interaction · Computer Science 2026-03-12 Yuxuan Lu , Ting-Yao Hsu , Hansu Gu , Limeng Cui , Yaochen Xie , William Headden , Bingsheng Yao , Akash Veeragouni , Jiapeng Liu , Sreyashi Nag , Jessie Wang , Dakuo Wang

Navigating complex urban environments using natural language instructions poses significant challenges for embodied agents, including noisy language instructions, ambiguous spatial references, diverse landmarks, and dynamic street scenes.…

Robotics · Computer Science 2026-01-16 Yanghong Mei , Yirong Yang , Longteng Guo , Qunbo Wang , Ming-Ming Yu , Xingjian He , Wenjun Wu , Jing Liu

While large language models (LMs) have shown remarkable capabilities across numerous tasks, they often struggle with simple reasoning and planning in physical environments, such as understanding object permanence or planning household…

Computation and Language · Computer Science 2023-10-31 Jiannan Xiang , Tianhua Tao , Yi Gu , Tianmin Shu , Zirui Wang , Zichao Yang , Zhiting Hu

Web agents have emerged as a promising direction to automate Web task completion based on user instructions, significantly enhancing user experience. Recently, Web agents have evolved from traditional agents to Large Language Models…

Computation and Language · Computer Science 2025-03-25 Hongru Cai , Yongqi Li , Wenjie Wang , Fengbin Zhu , Xiaoyu Shen , Wenjie Li , Tat-Seng Chua

Most prior works on communication in multi-agent reinforcement learning have focused on emergent communication, which often results in inefficient and non-interpretable systems. Inspired by the role of language in natural intelligence, we…

Multiagent Systems · Computer Science 2025-08-08 Maxime Toquebiau , Jae-Yun Jun , Faïz Benamar , Nicolas Bredeche

LLM agents achieve 85-96% success on tasks where instructions fully specify the action, but drop to 29-53% when action feasibility depends on environmental state that the instruction does not mention. We argue that this gap reflects a…

Computation and Language · Computer Science 2026-05-29 Zixuan Wang , Dingming Li , Hongxing Li , Yanrui Miao , Shuo Chen , Yuchen Yan , Wenqi Zhang , Yongliang Shen , Weiming Lu , Jun Xiao , Yueting Zhuang

Text Worlds are virtual environments for embodied agents that, unlike 2D or 3D environments, are rendered exclusively using textual descriptions. These environments offer an alternative to higher-fidelity 3D environments due to their low…

Computation and Language · Computer Science 2021-07-12 Peter A Jansen

Scaling Visual Question Answering (VQA) to the open-domain and multi-hop nature of web searches, requires fundamental advances in visual representation learning, knowledge aggregation, and language generation. In this work, we introduce…

Computation and Language · Computer Science 2022-03-29 Yingshan Chang , Mridu Narang , Hisami Suzuki , Guihong Cao , Jianfeng Gao , Yonatan Bisk