Final Project
Objective:
The goal of this project is to design and run a simulation using generative agents. We've compiled an agent bank that represents the members of the class, which you can choose to use if you wish. You will explore a research question using generative agents, drawing insights into behaviors, preferences, or interactions in a certain setting.
Project Overview:
Each group will use generative agents, either those that were created during the class or those you've created, to simulate behaviors and interactions. You’ll develop a research question around the capabilities and limitations of generative agents in simulating human behavior, such as decision-making, collaboration, or opinion diversity, and use the agents to conduct experiments, surveys, or social simulations that help answer that question.
Steps:
Team Formation:
- Group Size: 3-4 students.
- Group Composition: Ensure a balance of skills within your group (e.g., data analysis, programming, interpretation).
Research Question Development:
Choose a research question that explores something meaningful about human behavior, agents, and/or simulations. A few examples that utilize the class agent bank might include:
- How do different personality traits affect group collaboration in problem-solving tasks?
- Can we simulate how class opinions might change on a controversial topic over time?
- What types of group dynamics emerge when agents with differing opinions or backgrounds work together on a project?
Your research question should guide how you’ll use the generative agents to simulate interactions or responses, and should be situated in the context of prior work in that area. You should also consider how you will analyze the results of your simulation.
Simulation Design:
Design a simulation, survey, or experiment using the agents. Possible methods include:
- Running an interaction between agents (e.g., simulating group discussions, voting, or problem-solving).
- Creating and analyzing responses to a survey that the agents will complete.
- Investigating emergent behaviors or patterns by running a series of interactions between agents.
Be creative! The project is open-ended. Feel free to ask us for help or to explore other simulations or experiments that you think might be interesting.
Running the Simulation:
If you choose to use the agents that represent each of your classmates, you’ll have access to the full agent bank, including interview data and agent models, which can be queried to simulate decisions or responses. Otherwise, you can create your own agents using the framework we've provided.
Record the outputs of the simulation (e.g., survey results, interaction logs) and analyze the findings in relation to your research question.
Analysis and Reflection:
Analyze the simulation outcomes. What did you learn through the behavior of the agents? How did the simulation reflect or differ from real-life dynamics?
Reflect on the effectiveness of the agents in representing their real-life counterparts and discuss any limitations or improvements.
Key Deliverables:
- Due: November 6, 2024.
- Submit a 1-2 page proposal using the template on Canvas that includes:
- Your research question.
- The methodology for how you plan to use the generative agents in your simulation.
- A brief explanation of what insights you hope to gain from the project.
Final Presentation (30%):
- Date: December 2 & 4, 2024.
- Present your project and findings to the class. Your presentation should include:
- An overview of your research question and the purpose of the simulation.
- A walk-through of how you used the generative agents.
- The results and insights from the simulation.
- A reflection on the accuracy and utility of the agents.
Final Submission (60%):
- Due: December 6, 2024.
- Your final submission should include:
- A written report (6-10 pages) detailing your process, findings, and reflections.
- Screenshots, logs, or data visualizations from your simulation.
- A discussion on the validity of the simulation and any lessons learned.
Grading Breakdown:
- Proposal (10%): Graded on clarity, creativity, and the feasibility of the research question and proposed method.
- Final Presentation (30%): Assessed based on how well you communicated your process, results, and insights. Depth of analysis and the ability to engage with classmates during the presentation will also be evaluated.
- Final Submission (60%):
- Methodology and Design (20%): How well the group utilized the generative agents to explore their research question.
- Results and Analysis (20%): The quality of the analysis, interpretation of results, and insights gained from the simulation.
- Reflection and Lessons Learned (20%): A thoughtful discussion on the limitations of the project, as well as potential improvements or extensions.
Important Dates:
- Proposal Deadline: 11/6/2024
- Final Presentation: 12/2/2024 and 12/4/2024
- Final Project Submission: 12/6/2024
Additional Considerations:
Optional Project Modifications:
If you have an alternative project idea that still utilizes the generative agents in a meaningful way, please check with your CA to ensure it meets the project goals.
Ethical Considerations:
Even though the generative agents are based on your classmates, ensure that your simulation and analysis maintain respect and privacy. Avoid sensitive topics or potentially uncomfortable scenarios.