Web Agents

Follow this topic Ask about this topic

Web agents study how AI systems can carry out multi-step tasks on websites, from finding information to filling forms and making purchases. Common approaches combine visual or DOM-based page understanding with planning, action grounding, memory, and reusable skills; training often uses human demonstrations, synthetic environments, or reinforcement learning. Benchmarks such as WebArena, Mind2Web, and WebVoyager measure task success, while live-web tests expose challenges from changing interfaces and complex workflows. A central tension is improving reliability and efficiency without compromising security, privacy, or faithful execution of user intent.

Latest papers

174 papers23 papers in the last four weeks, up 53% on the four weeks before. 0.1% of all new papers.

MEMENTO: Leveraging Web as a Learning Signal for Low-Data Domains
May 28, 2026Ashutosh Ojha, Vinay Aggarwal, Ashutosh Srivastava +3Lifelong Learning Agents Agent Skill Learning
Adobe, Media & Data Science Research Lab
Revisiting Observation Reduction for Web Agents: Comprehensive Evaluation with a Lightweight Framework
May 28, 2026Masafumi Enomoto, Ryoma Obara, Haochen Zhang +1Web Agent Benchmarks LLM Agent Evaluation
NEC Corporation
GTA: Generating Long-Horizon Tasks for Web Agents at Scale
May 28, 2026Tenghao Huang, Kung-Hsiang Huang, Prafulla Kumar Choubey +4Computer-Use Agent Benchmarks Web Agent Benchmarks
University of Southern California · Salesforce AI Research · University of California, Davis
PANDO: Efficient Multimodal AI Agents via Online Skill Distillation
May 24, 2026Yubo Li, Yidi Miao, Yuntian Shen +1LLM Agent Workflow Optimization LLM Agent Skill Learning
Weasel: Out-of-Domain Generalization for Web Agents via Importance-Diversity Data Selection
May 19, 2026Fatemeh Pesaran Zadeh, Seyeon Choi, Xing Han Lù +2Diversity-Aware Sampling OOD Generalization
Seoul National University · McGill University · Mila – Quebec AI Institute +1
SimGym: A Framework for A/B Test Simulation in E-Commerce with Traffic-Grounded VLM Agents
May 19, 2026Han Li, Vibhor Malik, Zahra Zanjani Foumani +17Tool-Using Vision-Language Agents A/b Testing
Shopify, Bellevue, Washington, USA
Skim: Speculative Execution for Fast and Efficient Web Agents
May 15, 2026Mike Wong, Kevin Hsieh, Suman Nath +1LLM Inference Efficiency LLM Agent Workflow Optimization
Princeton University · Princeton, USA · Microsoft Research +1
ShopGym: An Integrated Framework for Realistic Simulation and Scalable Benchmarking of E-Commerce Web Agents
May 15, 2026Chinmay Savadikar, Mingyu Zhao, Yuanzheng Zhu +5Benchmark Design Web Agent Benchmarks
North Carolina State University · Shopify
Web Agents Should Adopt the Compile-and-Execute Paradigm
May 14, 2026Julien Piet, Annabella Chow, Yiwei Hou +5LLM Agent Safety LLM Agent Planning
UC Berkeley
SimPersona: Learning Discrete Buyer Personas from Raw Clickstreams for Grounded E-Commerce Agents
May 14, 2026Zahra Zanjani Foumani, Alberto Castelo, Shuang Xie +3LLM Personalization Vector-Quantized Variational Autoencoder
Shopify · Bellevue, Washington, USA
LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues
May 12, 2026Di Wu, Zixiang Ji, Asmi Kawatkar +4Computer-Use Agent Benchmarks Retrieval-Augmented Generation
University of California, Los Angeles
IPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt Injection
May 12, 2026Chia-Pei, Chen, Kentaroh Toyoda +2AI Agent Security AI Agent Security Benchmarks
Janet · Vulcan Research, AIFT
Don't Click That: Teaching Web Agents to Resist Deceptive Interfaces
May 10, 2026Yilin Zhang, Yingkai Hua, Chunyu Wei +2Adversarial Robustness AI Agent Security
Renmin University of China · Ant Digital Technologies, Ant Group
WebTrap: Stealthy Mid-Task Hijacking of Browser Agents During Navigation
May 8, 2026Zhichao Liu, Wenbo Pan, Haining Yu +3Indirect Prompt Injection Prompt Injection Attacks
Harbin Institute of Technology · City University of Hong Kong · City University of Macau
Region4Web: Rethinking Observation Space Granularity for Web Agents
May 8, 2026Donguk Kwon, Dongha LeeWeb Agents
Yonsei University
Weblica: Scalable and Reproducible Training Environments for Visual Web Agents
May 7, 2026Oğuzhan Fatih Kar, Roman Bachmann, Yuanzheng Gong +2LLM Agent Training RL for LLM Agents
Apple
cotomi Act: Learning to Automate Work by Watching You
May 4, 2026Masafumi Oyamada, Kunihiro Takeoka, Kosuke Akimoto +5Agent Memory Computer-Use Agents
NEC Corporation
BaRA: Budget-constrained and Reliable Web Data Collection Agent
May 2, 2026Soojeong Lee, Joseph Lee, Yongseong Cho +3Multimodal Agents Web Agents
Department of Statistics and Data Science, Yonsei University, Seoul, Republic of Korea · Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea · HUSTLERS Corp., Seoul, Republic of Korea
AutoSurfer -- Teaching Web Agents through Comprehensive Surfing, Learning, and Modeling
Apr 29, 2026Fazle Elahi Faisal, Qianhui Wu, Baolin Peng +1LLM Agent Training Web Agents
Microsoft Research
SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents
Apr 28, 2026Mengyao Du, Han Fang, Haokai Ma +4Indirect Prompt Injection Prompt Injection Detection
1National University of Defense Technology · University of Science and Technology of China · 3National University of Singapore +1
DRIVE: Modeling Skills at the Reasoning and Interaction Levels for Web Agents under Continual Learning
Apr 28, 2026Xirui Liu, Sihang Zhou, Yanning Hou +6Continual Learning for LLM Agents LLM Agent Skill Learning
College of Intelligence Science and Technology, National University of Defense Technology, Changsha, 410073, Hunan, China · College of Computer Science and Technology, National University of Defense Technology, Changsha, 410073, Hunan, China
Infrastructure for the Agentic Web: Gap Analysis and Architecture from the Agentverse Platform
Apr 26, 2026Robin Dey, Panyanon ViradechaWeb Agents
OpenHub Research Chiang Mai, Thailand
Mango: Multi-Agent Web Navigation via Global-View Optimization
Apr 20, 2026Weixi Tong, Yifeng Di, Tianyi ZhangMulti-Agent Systems Web Agents
Purdue University
WebUncertainty: Dual-Level Uncertainty Driven Planning and Reasoning For Autonomous Web Agent
Apr 20, 2026Lingfeng Zhang, Yongan Sun, Jinpeng Hu +5Web Search Agents Monte Carlo Tree Search
Hefei University of Technology · Academy of Cyber, CETC Group
MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation
Apr 16, 2026Yan Li, Zezi Zeng, Yifan Yang +12Web Application Generation Web Agent Benchmarks
Shanghai Jiao Tong University · Xi’an Jiaotong University · Microsoft Corporation +1
WebXSkill: Skill Learning for Autonomous Web Agents
Apr 14, 2026Zhaoyang Wang, Qianhui Wu, Xuchao Zhang +12LLM Agent Skill Learning Long-Horizon LLM Agents
University of North Carolina at Chapel Hill · Microsoft
From Imitation to Discrimination: Progressive Curriculum Learning for Robust Web Navigation
Apr 14, 2026Chuang Peng, Wei Zhang, Renshuai Tao +2Web Agents LLM Agent Training
Beijing Jiaotong University · Beihang University
AgentWebBench: Benchmarking Multi-Agent Coordination in Agentic Web
Apr 13, 2026Shanshan Zhong, Kate Shen, Chenyan XiongWeb Agent Benchmarks Web Agents
Language Technologies Institute, School of Computer Science, Carnegie Mellon University · Anaxi Labs
ClawBench: Can AI Agents Complete Everyday Online Tasks?
Apr 9, 2026Yuxuan Zhang, Yubo Wang, Yipeng Zhu +25Web Agent Benchmarks AI Agent Evaluation
University of British Columbia · Vector Institute · Etude AI +9
MolmoWeb: Open Visual Web Agent and Open Data for the Open Web
Apr 9, 2026Tanmay Gupta, Piper Wolters, Zixian Ma +13Web Agents LLM Agent Training
Allen Institute for AI · University of Washington · UNC-Chapel Hill

May 28, 2026J/K move · Enter open · S save

MEMENTO: Leveraging Web as a Learning Signal for Low-Data Domains

Ashutosh Ojha, Vinay Aggarwal, Ashutosh Srivastava, Siddharth Yedlapati+2

Adobe, Media & Data Science Research Lab

Lifelong Learning Agents Agent Skill Learning Memory-Augmented Agents Web Agents Data-Efficient Learning

Open paper AskPDF arXiv

Real-world tasks often lack large labeled datasets, motivating extensive work on learning in low-data regimes. Existing approaches such as few-shot prompting, instruction tuning, and synthetic data generation, continue to treat labeled or pseudo-labeled data as the primary learning signal. In contrast, human practitioners acquire expertise through repeated, self-directed interaction with the open web, progressively refining both domain knowledge and search strategies. We propose MEMENTO, a framework that treats the web as a learning signal rather than a stateless retrieval interface. MEMENTO operates at two levels: within each session, it conducts iterative web exploration via an Adaptive Exploration Tree (AET) that decomposes tasks into evolving questions and reflects on intermediate findings; across sessions, it accumulates experience through dual-channel memory, separating declarative knowledge (facts) from procedural knowledge (search strategies). This design enables agents to learn reusable research strategies and domain expertise from trajectories of web interaction without additional model training. We evaluate MEMENTO on three structurally distinct low-data domains: Sales Automation, Legal Outcome Prediction, and Subpopulation Opinion Prediction. Our empirical results show consistent improvement in performance over ReAct baselines (+25.6% on sales, +36.5% on legal research, and 29.6% TVD reduction on opinion prediction), demonstrating that the web can serve as a scalable learning source for acquiring task-specific expertise in data-scarce settings.