Skip to content
All tags

#genie

2 posts
ai deep-dive Reading Stanford CS224V

Stanford CS224V Lecture 4: Task-Agent Evaluation Beyond Human-Like Answers

CS224V splits task-agent evaluation into state updates and complete interaction: isolate the semantic parser, then test task completion, grounded queries, and valid actions with real users.

#cs224v#stanford#agent-evaluation#task-oriented-dialogue#genie
ai deep-dive Reading Stanford CS224V

Stanford CS224V Lecture 3: Building Task-Oriented Agents with Genie Worksheets

Genie Worksheets declare task capability as a form-like specification. A contextual semantic parser updates formal dialogue state while the runtime controls queries, actions, and responses.

#cs224v#stanford#task-oriented-dialogue#semantic-parsing#genie