ucb_agentic_ai

Lecture 08: AI Agents for Accelerating Scientific Discoveries

Link to lecture recording on YouTube

Date: 2025-11-03

Speaker: James Zou

Speaker’s Social Profile: Website / Google Scholar / GitHub / LinkedIn / X (Twitter)

Education:

Work:

Notes

AI has been very successful as a tool across many domains of science

The Virtual Lab

A team of interdisciplinary AI scientists that work with human scientist on challenging, open-ended research

Example Virtual Lab team meeting:

Human researchers (Prof. Zou and students) wrote ~1.3% of the words; their job is to mostly provide high-level guidance to the AI agents

Virtual Lab School of self-improving AI scientists: frontier models behind these agents are good at broad general knowledge, but do not have the most up-to-date information or may not know how to use the latest tools in a specific technical or scientific domain

  1. first tell the agents the topics that they should learn about in the school
  2. for each of these topics, the agent would generate their own learning curriculum
  3. agents do web search for reference materials
  4. read and summarize papers
  5. do supervised fine-tuning to update model parameters
  6. teacher agents will generate quizzes to test how well the student agents learn the topic; if don’t do well, go back to school, do additional training and fine-tuning before they can graduate

[Incomplete, work in progress]

References