DeepRead
Search
Search
Dark mode
Light mode
Explorer
Popular Tags
#VLM
#agentic-RL
#gui-agent
#web-agent
#LLM
#VLA
#computer-use
#task-planning
#manipulation
#imitation-learning
Tag: preference-optimization
1 item with this tag.
Aug 20, 2026
TGPO: Tree-Guided Preference Optimization for Robust Web Agent Reinforcement Learning
web-agent
reinforcement-learning
preference-optimization
credit-assignment