1 minute read

WebRL: Training LLM Web Agents Via Self-Evolving Online Curriculum Reinforcement Learning

6 minute read

[WebAgent] WebRL: Training LLM Web Agents Via Self-Evolving Online Curriculum Reinforcement Learning

DesignCoder: Hierarchy-Aware and Self-Correcting UI Code Generation with Large Language Models

7 minute read

[GUI] DesignCoder: Hierarchy-Aware and Self-Correcting UI Code Generation with Large Language Models

[WebAgent] The BrowserGym Ecosystem for Web Agent Research

6 minute read

[WebAgent] The BrowserGym Ecosystem for Web Agent Research

Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement

3 minute read

[Seg] Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement