<aside> <img src="/icons/alien-pixel_green.svg" alt="/icons/alien-pixel_green.svg" width="40px" /> Home
</aside>
<aside> <img src="/icons/verified_green.svg" alt="/icons/verified_green.svg" width="40px" /> About PAPER
This channel is dedicated to building and expanding a comprehensive paper database focused on the Web Agent field and the boarder GUI agent field. Let’s collaborate to enrich this database and advance research in the exciting world of web agents!
</aside>
🔥 Newly updated（Apr）
New～Apr 09｜
New～Apr 09｜
New～Apr 09｜What’s Missing in Screen-to-Action? Towards a UI-in-the-Loop Paradigm for Multimodal GUI Reasoning
New～Apr 09｜Preference Redirection via Attention Concentration: An Attack on Computer Use Agents
New～Apr 09｜MolmoWeb: Open Visual Web Agent and Open Data for the Open Web
New～Apr 09｜Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection
New～Apr 10｜CORA: Conformal Risk-Controlled Agents for Safeguarded Mobile GUI Automation
New～Apr 09｜Structured Distillation of Web Agent Capabilities Enables Generalization
New～Apr 09｜ClawBench: Can AI Agents Complete Everyday Online Tasks?
New～Apr 09｜KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation
New～Apr 09｜Learning to Retrieve from Agent Trajectories
Apr 08｜SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills
New～Apr 07｜WebSP-Eval: Evaluating Web Agents on Website Security and Privacy Tasks
Apr 04｜ClawSafety: “Safe” LLMs, Unsafe Agents
Apr 07｜Gym-Anything: Turn any Software into an Agent Environment
Apr 07｜Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents
Apr 07｜Don’t Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correction
Apr 06｜IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents
Apr 06｜ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces
Apr 06｜UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics
Apr 06｜GUIDE: Interpretable GUI Agent Evaluation via Hierarchical Diagnosis
New～Apr 04｜The Art of Building Verifiers for Computer Use Agents
Apr 04｜GPA: Learning GUI Process Automation from Demonstrations
Apr 03｜The Tool Illusion: Rethinking Tool Use in Web Agents
Apr 02｜Read More, Think More: Revisiting Observation Reduction for Web Agents
Apr 01｜When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation