COMS6113: Topics in Agentic Systems
Overview
COMS6113 Topics in Agentic Systems is a research-oriented course on agentic AI systems: systems that can plan, call tools, coordinate with humans, and act across software, data, and organizational environments.
The course is targeted toward Ph.D. students and undergraduate or graduate students who are interested in doing research, especially students interested in producing a publication. Students should be ready to read research papers closely, discuss speculative ideas in class, and develop a semester-long research project.
The course will examine open research problems across the systems stack.
Broad questions include:
- What infrastructure do data systems and ML systems need to support agentic workloads?
- TBD
Course Structure
- Classes will combine paper discussion, research critique, project development, and research progress discussion.
- Students will read papers before class, answer or discuss questions, and participate actively.
- The semester-long project is a central part of the course.
- Slack and Google Slides will be used heavily for discussion, coordination, and course materials.
Schedule
| Week | Date | Topic |
|---|---|---|
| 1 | Sep 11 | TBD |
| 2 | Sep 18 | TBD |
| 3 | Sep 25 | TBD |
| 4 | Oct 2 | TBD |
| 5 | Oct 9 | TBD |
| 6 | Oct 16 | TBD |
| 7 | Oct 23 | TBD |
| 8 | Oct 30 | TBD |
| 9 | Nov 6 | TBD |
| 10 | Nov 13 | TBD |
| 11 | Nov 20 | TBD |
| 12 | Nov 27 | No class: Thanksgiving break |
| 13 | Dec 4 | Final project presentations |
| 14 | Dec 11 | No class |
Project
You will pursue a semester-long research project related to agentic systems. The project is a significant part of the course and is intended to lead to a publication.
Project goals:
- Identify a concrete research question about agentic systems.
- Build, analyze, evaluate, or critique a system, method, benchmark, or workflow.
- Connect the project to related research.
- Present results clearly to the class.
- Write the final result as a full publication-ready research paper.
Possible project areas include LLM serving for agents, agentic workflow optimization, using AI agents for system optimization, agentic sandbox development and optimization, and many more.
Syllabus
Course Expectations
Students are expected to actively participate in class discussions; participation is mandatory.
Students should be comfortable reading research papers; you will read, answer questions, and comment on the readings before class.
Students should be comfortable coding in large systems codebases.
Students should be comfortable conducting a research project and writing up the results as a full research paper.
This is a research-oriented course targeted toward Ph.D. students and undergraduate or graduate students interested in doing research, especially students interested in having a publication.
Grading
TBD
Participation
Participation is mandatory. The topics in the course are speculative and forward looking, so the real content comes from class discussion.
Slack
There will be heavy use of Slack.
You are expected to ask and answer questions on Slack.
Collaboration/Copying Policy
Refer to Columbia’s academic honesty policy if you are at all unsure.
For the research project you are highly encouraged to use AI tools as much as possible.
Your reviews must be written originally, and be based on your own understanding and thoughts about the reading. Copying or paraphrasing content written by others is not allowed.
FAQ
What kind of project will I do?
Every project must be about agentic systems. Projects should ask a concrete research question about systems that can plan, call tools, coordinate with humans, or act across software, data, or organizational environments.
Projects will be done in teams. The minimum team size is 3 students, so students should expect to find and convince at least two other students to work with them on a shared project idea.
How will projects be structured?
Each project will have a shepherd who meets weekly with the students. The shepherd will help the team refine the research question, scope the work, identify related work, make progress, and prepare deliverables.
Students are expected to make progress every week. Each lecture will include student progress presentations to the class, so teams should be prepared to regularly explain what they tried, what they learned, what did not work, and what they plan to do next.
The course will have multiple project deliverables throughout the semester, not only a final presentation or final paper.
Can I bring my own Ph.D. project?
No. The course project is not meant to be a way to continue an unrelated Ph.D. project. All course projects must be about agentic systems and must satisfy the project expectations for this class, including team formation, weekly shepherd meetings, regular in-class progress presentations, and intermediate deliverables.