Web agents based on large language models have demonstrated promising capability in automating web tasks. However, current web agents struggle to reason out sensible actions due to the limitations of predicting environment changes, and might not possess comprehensive awareness of execution risks, prematurely performing risky actions that cause losses and lead to task failure. To address these challenges, we propose WAC, a web agent that integrates model collaboration, consequence simulation, and feedback-driven action refinement. To overcome the cognitive isolation of individual models, we introduce a multi-agent collaboration process that enables an action model to consult a world model as a web-environment expert for strategic guidance; the action model then grounds these suggestions into executable actions, leveraging prior knowledge of environmental state transition dynamics to enhance candidate action proposal. To achieve risk-aware resilient task execution, we introduce a two-stage deduction chain. A world model, specialized in environmental state transitions, simulates action outcomes, which a judge model then scrutinizes to trigger action corrective feedback when necessary. Experiments show that WAC achieves absolute gains of 1.8% on VisualWebArena and 1.3% on Online-Mind2Web.
SERC: LDPC-Inspired Semantic Error Correction for Retrieval-Augmented Generation
Department of Information Communications Engineering, Hankuk University of Foreign Studies, Republic of Korea(韩国外国语大学信息通信工程系);Division of Computer Engineering, Hankuk University of Foreign Studies, Republic of Korea(韩国外国语大学计算机工程系);Department of Statistics, Hankuk University of Foreign Studies, Republic of Korea(韩国外国语大学统计学系)
From PowerPoint UI Sketches to Web-Based Applications: Pattern-Driven Code Generation for GIS Dashboard Development Using Knowledge-Augmented LLMs, Context-Aware Visual Prompting, and the React Framework
InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented Agents
Shanghai Jiao Tong University(上海交通大学);The Chinese University of Hong Kong(香港中文大学);Zhejiang University(浙江大学);University of Oxford(牛津大学);MemTensor (Shanghai) Technology Co., Ltd(MemTensor(上海)科技有限公司)
RAIR: Retrieval-Augmented Iterative Refinement for Chinese Spelling Correction
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);Zhongke Fanyu Technology Co., Ltd(中科泛语科技有限公司)
Detecting Miscitation on the Scholarly Web through LLM-Augmented Text-Rich Graph Learning
Chinese Academy of Sciences & City University of Hong Kong(中国科学院与香港城市大学);City University of Hong Kong(香港城市大学);Shenzhen University & Beijing Dongbi Data Technology(深圳大学与北京东碧数据技术);University of Chinese Academy of Sciences(中国科学院大学)
ACCESS: Prompt Engineering for Automated Web Accessibility Violation Corrections
Carlmont High School(卡尔蒙特高中);Crofton House School(克罗夫顿豪斯学校);Lynbrook High School(林布鲁克高中);International School of Zug and Luzern(楚格与卢塞恩国际学校);Columbia University(哥伦比亚大学);Taipei American School(台北美国学校);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of California Berkeley(加州大学伯克利分校)
Improving Context Fidelity via Native Retrieval-Augmented Reasoning
DIRO, Université de Montréal(蒙特利尔大学计算机科学与运筹学系);MetaGPT;Mila - Quebec AI Institute(米拉-魁北克人工智能研究所);McGill University(麦吉尔大学);Yale University(耶鲁大学);Canada CIFAR AI Chair(加拿大CIFAR人工智能教席)
AccessGuru: Leveraging LLMs to Detect and Correct Web Accessibility Violations in HTML Code
University of Stuttgart, Artificial Intelligence(斯图加特大学人工智能学院);Artificial Intelligence, University of Stuttgart(人工智能学院,斯图加特大学);University of Stuttgart(斯图加特大学);University of Southampton(南安普顿大学)
SearchAttack: Red-Teaming LLMs against Knowledge-to-Action Threats under Online Web Search
Institute of Computing Technology, CAS(计算技术研究所,中国科学院);University of Chinese Academy of Sciences(中国科学院大学);People's Public Security University of China(中国人民公安大学);University of Science and Technology of China(中国科学技术大学);Guangdong Laboratory of Artificial Intelligence and Digital Economy(广东人工智能与数字经济实验室);Tsinghua University(清华大学)
Ontology Memory-Augmented ASR Correction for Long Text-Speech Interleaved Conversations
Institute of Computing and Intelligence, Harbin Institute of Technology (Shenzhen), China(哈尔滨工业大学(深圳)计算与智能研究所);Shenzhen Loop Area Institute (SLAI), China(深圳环域研究所)
Accelerating Manufacturing Scale-Up from Material Discovery Using Agentic Web Navigation and Retrieval-Augmented AI for Process Engineering Schematics Design