TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows Paper • 2512.05150 • Published 23 days ago • 74
You Don't Know Until You Click:Automated GUI Testing for Production-Ready Software Evaluation Paper • 2508.14104 • Published Aug 17 • 1
Recon-Act: A Self-Evolving Multi-Agent Browser-Use System via Web Reconnaissance, Tool Generation, and Task Execution Paper • 2509.21072 • Published Sep 25 • 15
PreAct: Predicting Future in ReAct Enhances Agent's Planning Ability Paper • 2402.11534 • Published Feb 18, 2024 • 1