Overview

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

CardsList

191 papers21 papers in the last four weeks, level with the four weeks before. 0.2% of all new papers.

  1. Web$hell: A Unified Interface for Agentic Web Access

    Oct 9, 2026Sunghwan Kim, Deogyong Kim, Sangam Lee +2Web AgentsLLM Agent Harnesses

  2. When Charts Deceive Web Agents: A Paired Benchmark for Misleading Visualization-Grounded Tasks

    Oct 9, 2026Yisheng Li, Dongming Han, Hongkun Pan +5Web AgentsAI Agent Reliability

  3. AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model

    Oct 6, 2026Sarim Hashmi, Mukul Ranjan, Kshitij Mishra +3Adversarial TrainingSim-to-Real Transfer

  4. AMBER: Training Long-Horizon Web Agents through Append-Only Memory

    Oct 5, 2026Chinmay Savadikar, Zhaoyu Zhang, Mingyu Zhao +4Long-Horizon LLM AgentsAgent Memory Management

  5. AdaptArena: Evaluating Test-Time Personalization of Web Agents

    Sep 29, 2026Dongchan Shin, Xing Han Lù, Jiaqi Deng +7Web AgentsLLM Personalization

  6. WebPageBench: Event-Level Verification and Controlled UI-Variant Generation for Web Agents

    Sep 28, 2026Anton Emelyanov, Maria Tikhonova, Zaven Martirosian +2Web Agent BenchmarksGUI Agents

  7. Before Acting, Change the State: Prospective State Intervention for Web Agents under Deceptive Interfaces

    Sep 28, 2026Ruozhao Yang, Mingfei Cheng, Xiaofei XieAI Agent SafetyRuntime Enforcement for AI Agents

  8. AX is the New AEO

    Sep 28, 2026Ido Finder, Assaf Elovic, Gad Shalev +1Agentic CommerceWeb Agents

  9. Probe to Act: Elevating Browser-Use Agent via Active Visual Probing

    Sep 27, 2026Keliang Li, Heng Wang, Chen Hu +3Active PerceptionVisual Grounding

  10. AgentTell: Behavioural Side-Channel Leakage in Browser-Use Agents

    Sep 26, 2026Asif Shahriar, Md Nafiu Rahman, Sadif Ahmed +2Data LeakageAI Agent Security

  11. From Trajectories to Grounded Preferences: Process Preference Synthesis via Interaction Element Graphs for Web PRMs

    Sep 26, 2026Yangzhe Peng, Xiaoyang Wang, Yiyang Zhao +2Process Reward ModelsSynthetic Data Generation

  12. Constructing Challenging Browser-Use Tasks by Controlled Environment Interventions

    Sep 20, 2026Xunjian Yin, Tianchen Guan, Jinao Wang +8Web AgentsWeb Agent Benchmarks

  13. EconSkills: Studying Skill Transfer and Retrieval for Web Agents on Live Economic Data

    Sep 17, 2026Yinzhu Quan, Zefang LiuTask Transferability EstimationLLM Agent Skill Learning

  14. AutoTailor: Automatic, User-Aligned Capability Selection and Adaptation for Web Agents

    Sep 11, 2026Xinyun Cao, Adriana Szekeres, Fazle Elahi FaisalWeb AgentsLLM Agents

  15. Token Efficient Task Execution via Application Behavior Modeling for Web Agents

    Sep 11, 2026Alexandru Ianta, Eleni StrouliaWeb AgentsLLM Agent Workflow Optimization

  16. Discriminative World Models for Web Agents

    Sep 2, 2026Kelvin Li, Dhruv Pendharkar, Anish Pahilajani +6World ModelsWeb Agents

  17. Monitoring Web Agents Without Internal Signals: Observable Trajectories and Key-Step Supervision

    Sep 2, 2026Sitong Pan, Yipeng Shen, Yilin Lu +3AI Agent MonitoringProcess Supervision

  18. When and What to Teach: Budget-Aware Online Adaptation for Web Agents

    Aug 31, 2026Jianwei Zhang, Sihan Cao, Pengcheng Zheng +7Online Knowledge DistillationLLM Agent Training

  19. SCAFFOLD: Self-Improving Web Agents via Recursive Parametric Skill Abstraction

    Aug 31, 2026Bowei He, Xiaokun Zhang, Meng Ding +1Web AgentsLLM Agent Skill Learning

  20. Learning Simple Test-Time Environments for LLM Web Agents

    Aug 29, 2026Junxuan Li, Zijun Liu, Ziyi Huang +4LLM AgentsWeb Agents

  21. BrowserForge: Scaling Web Episode via Parallel Browser Sandboxes

    Aug 25, 2026Fei Tang, Huawen Shen, Zhiqiong Lu +7Web AgentsLLM Agent Trajectory Synthesis

  22. Training Needs Trustworthy Worlds: Verified Synthetic Web Environments for Agent Learning

    Aug 22, 2026Chenghao Zhang, Yuxi Cheng, Saisai Hu +3Reinforcement Learning with Verifiable RewardsWeb Agents

  23. Improving LLM-based Autonomous Web Agents with Filtering

    Aug 16, 2026Zhitong Guo, Jing Yu Koh, Ruiyu LiWeb Agents