Overview

LLMs have opened new possibilities of automated agents that plan and complete tasks on the user’s behalf. Such agents have the potential to usher in a new industrial revolution by automating organizational processes. However, agents are currently limited to soft-edge tasks that have large tolerances for error, and are too unreliable for hard-edge tasks, like in healthcare or enterprises, where accuracy and reliability are paramount. In short, what does it take for agents to be used in enterprises?

This graduate-level course will cut across the technology stack to examine the research questions that need to be answered for agents to be possible in real tasks that matter. Each session will review 1-3 papers or systems, and discuss research opportunities that arise from the gap between existing research and enterprise requirements. Topics will span systems (data systems and ML systems), AI (LLMs, agent-based planning), HCI, and theory (reinforcement learning, markets).

Broad questions include

• What mechanisms are data systems missing to support agents?
• How does human-computer interaction change when the human interacts with agents?
• How can knowledge throughout an organization be used to constrain and improve agentic planning?
• How can systems handle the 10-100x increase in load generated by agents?
• What are the theoretical limits of what agents can do?
• At scale, how will the use of agents affect markets, incentives, and the structure of organizations?

Due to the speculative nature of the course, students are expected to co-investigate the problems alongside the instructors.

Prereqs:

• Participants are expected to have exposure to LLM-agents, and expertise in another
• This is by default a PhD-level course due to its research and forward looking nature
• This seminar is open to undergraduates and MS students with demonstrated abilities to critically read research papers and ask good questions.

Information

• Class: Tu/Th 10:10-11:25AM, Loc TBA
• Instructors:
  • Eugene Wu
  • Kostis Kaffes
• Syllabus & FAQ, Slack, Project, Papers
• Prereqs: W4111 Intro to DB (required), W4112 DB Implementations (recommended). Ugrads OK; see Prof Wu

Grading

• Discussion Prep 30%
• Class participation 30%
• Project 40%: Final Presentation 10%, Paper 30%

Recent Announcements

Tentative Schedule

Date	Topic	Notes
C1: 1/21	Intro
C2: 1/23	tba
C3: 1/28	tba
C4: 1/30	tba
C5: 2/4	tba
C6: 2/6	tba
C7: 2/11	tba
C8: 2/13	tba
C9: 2/18	tba
C10: 2/20	tba
C11: 2/25	tba
C12: 2/27	tba
C13: 3/4	tba
C14: 3/6	tba
C15: 3/11	tba
C16: 3/13	tba
C17: 3/25	tba
C18: 3/27	tba
C19: 4/1	tba
C20: 4/3	tba
C21: 4/8	tba
C22: 4/10	tba
C23: 4/15	tba
C24: 4/17	tba
C25: 4/22	tba
C26: 4/24	tba
C27: 4/29	tba
C28: 5/1	tba Link to Presentation Guideline