An Illusion of Progress? Assessing the Current State of Web Agents

This paper argues that reported web-agent progress is overstated once agents are evaluated on more realistic online tasks. It introduces Online-Mind2Web with 300 tasks across 136 live websites, pairs it with the WebJudge automatic evaluation method, and uses that setup to show a much weaker picture of current web-agent capability than prior benchmarks suggest.

• ClawBench: Can AI Agents Complete Everyday Online Tasks?
  April 9, 2026 · arXiv
• Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos
  March 23, 2026 · CVPR 2026
• AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?
  October 21, 2024 · EMNLP 2024 (Poster)
• GUIDE: Interpretable GUI Agent Evaluation via Hierarchical Diagnosis
  April 6, 2026 · arXiv
• MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments
  February 3, 2026 · arXiv
• Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks
  April 27, 2026 · arXiv
• WebForge: Breaking the Realism-Reproducibility-Scalability Trilemma in Browser Agent Benchmark
  April 13, 2026 · arXiv
• The Amazing Agent Race: Strong Tool Users, Weak Navigators
  April 11, 2026 · arXiv
• Same Outcomes, Different Journeys: A Trace-Level Framework for Comparing Human and GUI-Agent Behavior in Production Search Systems
  April 9, 2026 · arXiv
• GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents
  April 8, 2026 · arXiv
• WebSP-Eval: Evaluating Web Agents on Website Security and Privacy Tasks
  April 7, 2026 · arXiv
• The Art of Building Verifiers for Computer Use Agents
  April 5, 2026 · arXiv
• When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation
  April 1, 2026 · arXiv
• WebArena-Infinity: Generating Browser Environments with Verifiable Tasks at Scale
  March 2026 · Blog Post
• Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification
  March 27, 2026 · arXiv
• WebTestBench: Evaluating Computer-Use Agents towards End-to-End Automated Web Testing
  March 26, 2026 · arXiv
• WebPII: Benchmarking Visual PII Detection for Computer-Use Agents
  March 18, 2026 · arXiv
• WebChain: A Large-Scale Human-Annotated Dataset of Real-World Web Interaction Traces
  March 5, 2026 · arXiv
• TimeWarp: Evaluating Web Agents by Revisiting the Past
  March 5, 2026 · arXiv
• Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History
  February 19, 2026 · arXiv
• PATHWAYS: Evaluating Investigation and Context Discovery in AI Web Agents
  February 5, 2026 · arXiv
• Avenir-Web: Human-Experience-Imitating Multimodal Web Agents with Mixture of Grounding Experts
  February 2, 2026 · arXiv
• WebTrap Park: An Automated Platform for Systematic Security Evaluation of Web Agents
  January 13, 2026 · arXiv
• WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks
  January 5, 2026 · arXiv