paper-with-me

Papers

InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training

2026-01-07 · Ziyun Zhang, Zezhou Wang, Xiaoyi Zhang, Zongyu Guo, Jiahao Li, Bin Li, Yan Lu arxiv

GUI agents that interact with graphical interfaces on behalf of users represent a promising direction for practical AI assistants. However, training such agents is hindered by the scarcity of suitable environments. We present InfiniteWeb, a system that automatically generates functional web environments at scale for GUI agent training. While LLMs perform well on generating a single webpage, building a realistic and functional website with many interconnected pages faces challenges. We address these challenges through unified specification, task-centric test-driven development, and a combination of website seed with reference design image to ensure diversity. Our system also generates verifiable task evaluators enabling dense reward signals for reinforcement learning. Experiments show that InfiniteWeb surpasses commercial coding agents at realistic website construction, and GUI agents trained on our generated environments achieve significant performance improvements on OSWorld and Online-Mind2Web, demonstrating the effectiveness of proposed system.

📄 PDF Abstract BibTeX arXiv:2601.04126

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

AutoForge: Automated Environment Synthesis for Agentic Reinforcement Learning

2025-12-28 · Shihao Cai, Runnan Fang, Jialong Wu, Baixuan Li 외 arxiv

Conducting reinforcement learning (RL) in simulated environments offers a cost-effective and highly scalable way to enhance language-based agents. However, previous work has been limited to semi-automated environment syn…

Reinforcement LearningDomain Generalization

Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence

2026-04-20 · Guanting Dong, Junting Lu, Junjie Huang, Wanjun Zhong 외 arxiv

Large language models are increasingly expected to serve as general-purpose agents that interact with external, stateful tool environments. The Model Context Protocol (MCP) and broader agent skills offer a unified interf…

Reinforcement Learning

GSAR: Goal-State-Anchor Rewards for Mobile GUI Agents with Self-Evolving Data Synthesis

2026-08-24 · Long Zhang, Yuhan Chen, Chaoran Zhang, Wanxia Cao 외 arxiv

Vision-Language Models (VLMs) based GUI agents stand to benefit significantly from online reinforcement learning (RL). However, their training is bottlenecked by two fundamental issues: current data synthesis methods for…

Reinforcement Learning

WebSynthesis: World-Model-Guided MCTS for Efficient WebUI-Trajectory Synthesis

2025-07-06 · Yifei Gao, Junhong Ye, Jiaqi Wang, Jitao Sang arxiv

Recent advancements in large language models (LLMs) have significantly improved the capabilities of web agents. However, effectively navigating complex and dynamic web environments still requires more advanced trajectory…

EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL

2026-05-18 · Minrui Xu, Zilin Wang, Mengyi DENG, Zhiwei Li 외 arxiv

Equipping LLMs with tool-use capabilities via Agentic Reinforcement Learning (Agentic RL) is bottlenecked by two challenges: the lack of scalable, robust execution environments and the scarcity of realistic training data…

Reinforcement Learning