CS329A: Self-Improving AI Agents
Stanford course on building AI agents that improve themselves over time through feedback, memory, and iterative refinement, in the context of large language models.
Stanford CS329A: Self-Improving AI Agents. The course explores how AI agents built on large language models can improve themselves over time, covering feedback loops, memory, self-reflection, and iterative refinement techniques for building agents that get better with experience rather than through retraining alone.
This is a curated third-party resource. All credit and citation belongs to Stanford University.