** Exact topics and schedule subject to change, based on student interests and course discussions. **

Date Topics Readings
9/9 Week 1 Course introduction
  • Basics of LLMs and foundation models
  • AI agents and self-evolution
9/16 Week 2 Context evolution 1
  • Prompt optimization
  • Memory, tools, knowledge
9/23 Week 3 Context evolution 2
  • LLMs as optimizers
  • LLMs for discovery
9/30 Week 4 Project proposal presentations
10/7 Week 5 Harness evolution 1
  • Harness components
  • Multi-agent systems
10/14 Week 6 Harness evolution 2
  • Self-evolving harnesses
10/21 Week 7 Member's week, no class
10/28 Week 8 Project midterm presentations
11/4 Week 9 Model evolution 1
  • Continual learning
  • Distillation
  • Test-time training
11/11 Week 10 Model evolution 2
  • Self-play approaches
11/18 Week 11 Task evolution 1
  • Synthetic data and tasks
  • Environment generation
11/25 Week 12 Task evolution 2
  • Evolving evaluation
  • Rewards
12/2 Week 13 Project final presentations
12/9 Week 14 Future topics
  • AI for scientific discovery
  • Embodied harnesses