flâneur

Stanford CS329A | Self-Improving AI Agents

cs329a.stanford.edu · 958 words · saved by 2 readers

This course covers the latest techniques and applications of AI agents that can continuously improve themselves through interaction with themselves and the environment. Our goal is that the students gain deep insights on building AI agents that take actions and use tools to solve interesting and challenging real-world problems. Most weeks there will be at least one Student Lecture. Each Student Lecture will consist of a team of 2 to 3 students that are responsible for reading all of the suggested reading and presenting a graded survey presentation (~45 Minutes). Format: 45 minute presentations followed by 15-20 minute Q&A sessions. As a graduate seminar, research is a big part of the class. Students will work in teams of 2 to 3 to complete original research. These projects should be broadly around agentic AI. Students will receive API credits to support their development work. Your final report is due on March 17, 9 p.m.. Audits are not allowed for this course.

Course Overview Autumn 2025 This course covers the latest techniques and applications of AI agents that can continuously improve themselves through interaction with themselves and the environment. The course will start with self-improvement techniques for LLMs, such as constitutional AI, using verifiers, scaling test-time compute, combining search with LLMs, and train time scaling with RL. We will then discuss the latest research in augmenting LLMs with tool use, code, and memory, and orchestrating AI capabilities with multimodal interaction. We will next discuss multi-step reasoning and…

saved by

related reading