WebRL: Training LLM Web Agents Via Self-Evolving Online Curriculum Reinforcement Learning
[WebAgent] WebRL: Training LLM Web Agents Via Self-Evolving Online Curriculum Reinforcement Learning
Recent posts
DesignCoder: Hierarchy-Aware and Self-Correcting UI Code Generation with Large Language Models
[GUI] DesignCoder: Hierarchy-Aware and Self-Correcting UI Code Generation with Large Language Models
[WebAgent] The BrowserGym Ecosystem for Web Agent Research
[WebAgent] The BrowserGym Ecosystem for Web Agent Research
Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement
[Seg] Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement
Webarena
[WebAgent] WebArena: A Realistic Web Environment for Autonomous Agents