Stanford launches CS 224V, an Agentic AI course tackling agent reliability with RAG and formal methods
stanfordnlp · x · 2026-10-02
Stanford's CS 224V "Agentic AI," taught by Monica Lam, kicks off in Fall 2026 as a lecture-plus-project course centered on making LLM agents reliable.
Topics include:
- Reducing hallucination in QA and task-oriented agents via RAG and formal task descriptions
- Hybrid knowledge reasoning across databases, knowledge bases, and unstructured text
- AI-driven knowledge curation and discovery for scientific research
- Improving decision-making agent accuracy and interpretability with formal methods
- Automated techniques for better long-horizon agents
The 3-4 unit course meets twice weekly with mandatory attendance, is waitlist-only, and requires prerequisites like CS 124/224N/224S/224U or Linguistics 180/280. Students complete a quarter-long research or domain-agent project.
More from coding & agent
- Workday opens its developer platform to indie devs for building AI agents on enterprise workflows — HeyNayeem · 2026-10-02
- One prompt, 8h 21min: Claude produces an 8-minute documentary, 96 takes, fully autonomous — GCWebDesigner · 2026-10-02
- After going all-in on agents, 9 of 11 sprint tickets are specced by PMs and built by AI — trvklhn666 · 2026-10-02
- ComfyUI Ships Comfy Agent to All Comfy Cloud Users: AI Plans, Builds and Fixes Workflows — cpaik · 2026-10-02
- Building a personal agent harness: the workflow matters more than the model — ghumare64 · 2026-10-02
- Surrendering to Claude Code's permission prompts: granting Bash(*) to all — Daniel_Farinax · 2026-10-02