Course positioning
CS 224V is a project-based agentic AI course with hard-core lectures, taught by Yuhao He and others. It is not about calling APIs; it systematically discusses agent reliability: reducing hallucination, mixing structured and unstructured knowledge, using formal methods to guarantee decisions, and optimizing long-horizon tasks.
What it covers
- RAG and task formalization: retrieval augmentation, formal task descriptions, reducing hallucination
- Hybrid knowledge reasoning: joint reasoning over databases, knowledge bases, and unstructured text
- AI-driven knowledge curation: organizing and discovering knowledge in scientific discovery
- Formal methods: improving the accuracy and interpretability of decision-making agents
- Long-horizon agents: automatically optimizing accuracy and efficiency on long tasks
- Quarter-long project: method research or a domain agent
Prerequisites
One of LINGUIST 180/280, CS 124, CS 224N, CS 224S, or CS 224U.
Assessment & workload
Lectures plus a quarter-long project that carries most of the grade (research or application). Check the current syllabus for details.
Who it's for
People who want to do agent research, AI scientists, or domain automation; anyone who knows LLM basics and wants to go deeper on reliability and formal guarantees.
Study advice
Get familiar with ReAct, Toolformer, RAG, and function calling first. Pick a quantifiable task for the project, or evaluation will be hard.
Related courses
Official course description
AI agents powered by Large Language Models (LLMs) are already transforming how we work, learn, and solve problems - and we are only at the beginning. As these systems grow more capable, they hold extraordinary promise for accelerating scientific discovery and democratizing access to high-quality medical, legal, and educational services worldwide. This is a project course coupled with rigorous lectures on the principles, methodologies, and cutting-edge research underlying agentic AI. Students undertake a substantial quarter-long project in either foundational methodology research or building novel agents in a domain of their choice. Topics covered include: (1) minimizing hallucination in question-answering and task-oriented agents using Retrieval-Augmented Generation (RAG) and formal task descriptions; (2) hybrid knowledge reasoning over databases, knowledge bases, and unstructured text; (3) AI-driven knowledge curation and discovery for scientific research; (4) improving the accuracy and interpretability of decision-making agents through formal methods; and (5) automated techniques for improving the accuracy and efficiency of long-horizon agents. Prerequisites: one of LINGUIST 180/280, CS 124, CS 224N, CS 224S, or CS 224U.