Education

August 2020 - June 2025Ph.D. in Human Computer Interaction
Carnegie Mellon University
Advisors: Dominik Moritz, Adam Perer
Thesis: Interactive Data Profiling

August 2020 - May 2023M.S. in Human Computer Interaction
Carnegie Mellon University
Advisors: Dominik Moritz, Adam Perer

August 2016 — May 2020B.S. in Computer Science
Georgia Institute of Technology
GPA: 4.0, Summa Cum Laude, threads in Intelligence and Modeling/Simulation

Industry Experience

August 2025 - PresentMicrosoft Research, Redmond, WA
Senior Software Engineer, AI Frontiers
Research engineer working on AI agents, multi-agent systems, AI evaluations, and environments.

Summer 2024Microsoft Research, Redmond, WA
Research Intern, AI Frontiers - HAX Group
Mentor: Gagan Bansal, Victor Dibia
Research intern working on developer tools for multi-agent AI systems.

Summer 2022Databricks, San Francisco, CA
Software Engineering Contractor
Mentor: Kanit Wongsuphasawat
Designed and delivered production feature for creating dashboards by specifying fields of interest in a dataset.

Summer 2021Microsoft Research, Redmond, WA
Research Intern, VIDA Group
Mentor: Steve Drucker, Rob DeLine
Research intern working on data science tools. Lead project around reuse and sharing in data science, published at ICSE 2022. Co-author on project around visualizing data frame differences published at CHI 2022.

Summer 2019Point72 Asset Management, New York, NY
Data Analytics Intern, Market Intelligence Group
Mentor: Trevor Rempel
Worked as Data Scientist in alternative data space to clean, model, and understand large datasets

Summer 2018Ultimate Software, Weston, FL
Software Development Intern, Innovation Strategies Team
Mentor: Joseph Cutrono
Designed and developed Slack app to integrate with the UltiPro HR management tool. App published to Slack app store.

Summer 2015The Home Depot, Atlanta, GA
Software Development Intern
Developed web app for tracking candidate progress throughout hiring process for internal HR use.

Research Experience

August 2020 - June 2025Carnegie Mellon University, Pittsburgh, PA
Graduate Researcher, Data Interaction Group (DIG)
Advisor: Dominik Moritz, Adam Perer
Member of the DIG research group, working on novel data visualizations, ML interpretation techniques, and interactive data systems.

January 2019 - May 2020Georgia Institute of Technology, Atlanta, GA
Undergraduate Researcher, Polo Club of Data Science
Advisor: Duen Horng (Polo) Chau
Member of the Polo Club of Data Science working on novel data visualizations to find fairness issues in Machine Learning models

January 2018 - May 2019Georgia Institute of Technology, Atlanta, GA
Undergraduate Researcher, Automated Algorithm Design
Advisor: Jason Zutty, Greg Rohling
Worked on EMADE algorithm design engine to implement sentiment analysis pipeline to analyze news articles to aid in predicting stock price movements using genetic algorithms. Led project to visualize the genetic algorithm evolution process.

Publications

SocialReasoning-Bench: Measuring Whether AI Agents Act in Users’ Best Interests
Tyler Payne, Will Epperson, Safoora Yousefi, Zachary Huang, Gagan Bansal, Wenyue Hua, Maya Murad, Asli Celikyilmaz, Saleema Amershi
A benchmark for measuring AI agents’ negotiation ability in calendar coordination and marketplace settings.
Microsoft Research Blog. 2026.
Project Blog Code

Whimsical Strategies Break AI Agents: Generating Out-of-Distribution Adversarial Strategies at Scale
Zachary Huang, Tyler Payne, Gagan Bansal, Will Epperson, Wenyue Hua, Adam Fourney, Amanda Swearngin, Maya Murad, Ece Kamar, Saleema Amershi
Automatically generating out-of-distribution adversarial strategies that reliably manipulate frontier agents in negotiations.
Microsoft Research Blog. 2026.
Project Blog

Red-Teaming a Network of Agents: Understanding What Breaks When AI Agents Interact at Scale
Gagan Bansal, Shujaat Mirza, Keegan Hines, Will Epperson, Zachary Huang, Whitney Maxwell, Pete Bryan, Tyler Payne, Adam Fourney, Amanda Swearngin, Wenyue Hua, Tori Westerhoff, Amanda Minnich, Maya Murad, Ece Kamar, Ram Shankar Siva Kumar, Saleema Amershi
We evaluated a live network of over 100 always on AI agents and found new failure modes that only emerge at the network level.
Microsoft Research Blog. 2026.
Project Blog

Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets
Gagan Bansal, Wenyue Hua, Zezhou Huang, Adam Fourney, Amanda Swearngin, Will Epperson, Tyler Payne, Jake M. Hofman, Brendan Lucier, Chinmay Singh, Markus Mobius, Akshay Nambi, Archana Yadav, Kevin Gao, David M. Rothschild, Aleksandrs Slivkins, Daniel G. Goldstein, Hussein Mozannar, Nicole Immorlica, Maya Murad, Matthew Vogel, Subbarao Kambhampati, Eric Horvitz, Saleema Amershi
An open-source simulation environment for studying how LLM agents behave as buyers and sellers in two-sided markets.
Preprint. 2025.
Project PDF Code

@article{bansal2025magentic,
  title={Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets},
  author={Bansal, Gagan and Hua, Wenyue and Huang, Zezhou and Fourney, Adam and Swearngin, Amanda and Epperson, Will and Payne, Tyler and Hofman, Jake M. and Lucier, Brendan and Singh, Chinmay and Mobius, Markus and Nambi, Akshay and Yadav, Archana and Gao, Kevin and Rothschild, David M. and Slivkins, Aleksandrs and Goldstein, Daniel G. and Mozannar, Hussein and Immorlica, Nicole and Murad, Maya and Vogel, Matthew and Kambhampati, Subbarao and Horvitz, Eric and Amershi, Saleema},
  journal={arXiv preprint arXiv:2510.25779},
  year={2025}
}

Interactive Data Profiling
Will Epperson
My PhD thesis on interactive systems to help users automatically understand their data while programming.
Carnegie Mellon University (CMU). Pittsburgh, PA, 2025.
Project PDF

Texture: Structured Exploration of Text Datasets
Will Epperson, Arpit Mathur, Dominik Moritz, Adam Perer
Texture is a general purpose text exploration tool with interactions for using LLMs to derive data from text.
Open source. 2025.
Project PDF Code

Interactive Debugging and Steering of Multi-Agent AI Systems
Will Epperson, Gagan Bansal, Victor Dibia, Adam Fourney, Jack Gerrits, Erkang Zhu, Saleema Amershi
AGDebugger is an interactive debugging tool for multi-agent AI systems.
2025 CHI Conference on Human Factors in Computing Systems (CHI). Yokohama, Japan, 2025.
Project PDF Code

Over-Relying on Reliance: Towards Realistic Evaluations of AI-Based Clinical Decision Support
Venkatesh Sivaraman, Katelyn Morrison, Will Epperson, Adam Perer
We discuss how evaluations of human-AI decision support systems can move beyond reliance as the primary metric.
2025 CHI Workshop on HCI+Health (CHI). Yokohama, Japan, 2025.
Project PDF

Guided Statistical Workflows with Interactive Explanations and Assumption Checking
Yuqi Zhang, Adam Perer, Will Epperson
GuidedStats is a Jupyter extension that helps data scientists perform statistical analyses with guided workflows.
VIS 24: IEEE Conference on Data Visualization (VIS). St Pete Beach, Florida, 2024.
Project PDF Code

Dead or Alive: Continuous Data Profiling for Interactive Data Science
Will Epperson, Vaishnavi Gorantla, Dominik Moritz, Adam Perer
AutoProfiler is a Jupyter extension that helps data scientists understand their data and find issues during analysis through continuous data profiling.
VIS 23: IEEE Conference on Data Visualization (VIS). Melbourne, Australia, 2023.
Project PDF Code Best Paper Honorable Mention

A Declarative Specification for Authoring Metrics Dashboards
Will Epperson, Kanit Wongsuphasawat, Allison Whilden, Fan Du, Justin Talbot
Quick dashboarding presents a novel specification for dashboard authoring, comprised of sections of metrics combined with dimensions.
VDS at VIS 23: Visual Data Science Symposium (VDS). Melbourne, Australia, 2023.
Project PDF Best Paper

Leveraging Analysis History for Improved In Situ Visualization Recommendation
Will Epperson, Doris Jung-Lin Lee, Leijie Wang, Kunal Agarwal, Aditya Parameswaran, Dominik Moritz, Adam Perer
Solas is a visualization recommendation tool that uses the history of analysis for in situ recommendations in Jupyter.
EuroVis 22: Eurographics Conference on Visualization (EuroVis). Rome, Italy, 2022.
Project PDF Code

@article{Epperson22Solas,
  title={Leveraging Analysis History for Improved In Situ Visualization Recommendation},
  author={Epperson, Will and Lee, Doris Jung-Lin and Wang, Leijie and Agarwal, Kunal and Parameswaran, Aditya and Moritz, Dominik and Perer, Adam},
  journal={EuroVis 22: Eurographics Conference on Visualization},
  year={2022},
  publisher={EG}
  url={}
}

Strategies for Reuse and Sharing among Data Scientists in Software Teams
Will Epperson, April Yi Wang, Robert DeLine, Steven M. Drucker
Interviews and a survey with 149 data scientists at Microsoft revealed five distinct strategies for sharing and reusing analysis code along with factors that encourage or discourage reuse.
ICSE 22: ACM International Conference on Software Engineering (ICSE). Pittsburgh, PA, 2022.
Project PDF Recording Slides

@article{wang2022DITL,
  title={Strategies for Reuse and Sharing among Data Scientists in Software Teams},
  author={Epperson, Will and Wang, April Yi and DeLine, Robert and Drucker, Steven M.},
  journal={ICSE 22: ACM International Conference on Software Engineering},
  year={2022},
  publisher={ACM}
  url={}
}

Diff in the Loop: Supporting Data Comparison in Exploratory Data Analysis
April Yi Wang, Will Epperson, Robert DeLine, Steven M. Drucker
Diff in the Loop supports tracking, comparing, and visualizing differences in datasets during iterative data analysis.
SIGCHI 22: ACM Symposium on Computer Human Interaction (CHI). New Orleans, LA, 2022.
Project PDF

@article{wang2022DITL,
  title={Diff in the Loop: Supporting Data Comparison in Exploratory Data Analysis},
  author={Wang, April Yi and Epperson, Will, and DeLine, Robert and Drucker, Steven M.},
  journal={SIGCHI 22: ACM Symposium on Computer Human Interaction},
  year={2022},
  publisher={ACM}
  url={}
}

RECAST: Interactive Auditing of Automatic Toxicity Detection Models
Austin P. Wright, Omar Shaikh, Haekyu Park, Will Epperson, Muhammed Ahmed, Stephane Pinel, Diyi Yang, Duen Horng (Polo) Chau
Interactive Auditing of Automatic Toxicity Detection Models
24th ACM Conference on Computer-Supported Cooperative Work & Social Computing. 2021.
Project PDF

@article{wright2020recast,
title={RECAST: Interactive Auditing of Automatic Toxicity Detection Models},
author={Austin P. Wright and Omar Shaikh and Haekyu Park and Will Epperson and Muhammed Ahmed and Stephane Pinel and Diyi Yang and Duen Horng (Polo) Chau},
year={2020},
eprint={2001.01819},
archivePrefix={arXiv},
primaryClass={cs.CL}
}

FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learning
Angel Cabrera, Will Epperson, Fred Hohman, Minsuk Kahng, Jamie Morgenstern, Duen Horng (Polo) Chau
Discovering intersectional ML Bias through interactive visualization.
IEEE Conference on Visual Analytics Science and Technology (VAST). Vancouver, Canada, 2019.
Project Demo PDF Blog Recording Code

@article{cabrera2019fairvis,
  title={FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learning},
  author={Cabrera, {\'A}ngel and Epperson, Will, and Hohman, Fred and Kahng, Minsuk and Morgenstern, Jamie and Chau, Duen Horng},
  journal={IEEE Conference on Visual Analytics Science and Technology (VAST)},
  year={2019},
  publisher={IEEE}
  url={https://poloclub.github.io/FairVis/}
}

Talks

Interactive Data Profiling for Python DataFrames with AutoProfiler and Texture
May 2024PyCON 2024

Dead or Alive: Continuous Data Profiling for Interactive Data Science
October 2023VIS 23: IEEE Visualization Conference

A Declarative Specification for Authoring Metrics Dashboards
October 2023VDS at VIS 23: Visual Data Science Symposium

Leveraging Analysis History for Improved In Situ Visualization Recommendation
June 2022EuroVis 22: Eurographics Conference on Visualization

Strategies for Reuse and Sharing among Data Scientists in Software Teams
May 2022ICSE 22: ACM International Conference on Software Engineering

FairVis
October 2019VIS 19: IEEE Visualization Conference

Honors and Awards

2019PURA: President's Undergraduate Research Award
$1500 research grant to continue work on FairVis project

2016Stamps President's Scholarship
Full ride scholarship given to 40 incoming freshman at Georgia Tech

Mentees

During my PhD, I have had the pleasure of mentoring the following undergraduate and masters students on research projects.

Summer 2021 - Fall 2021Leijie Wang
Visualization recommendation for python in notebooks using history

Fall 2021 - Spring 2022Asad Sheikh
Visualization recommendation for SQL using history

Spring 2022 - Spring 2023Vaishnavi Gorantla
Fact generation from data and presentation as text

Spring 2023 - Spring 2024Yuqi Zhang
Notebook extension for guided statistical analysis

Summer 2023 - Spring 2024Allie Feldman
Guided Data Analysis

Teaching

Spring 2023 Graduate Teaching Assistant
Carnegie Mellon University, Pittsburgh, PA
Programmable User Interfaces, Instructor: Scott Hudson
Taught recitation, designed assignments for class about UI design and intro HTML, CSS, & Javascript.

Fall 2022 Graduate Teaching Assistant
Carnegie Mellon University, Pittsburgh, PA
Interactive Data Science, Instructor: Adam Perer and John Stamper
Graded and office hours for class about using jupyter, visualization, steamlit and related tech for data science.

August 2017 - December 2018 Undergraduate Teaching Assistant
Georgia Institute of Technology, Atlanta, GA
Intro to Database Systems (CS 4400), Instructor: Monica Sweat
Designed projects, held office hours and graded for relational databases class.

Service

Reviewer for CHI 2025, VIS 2024, VIS 2023, CHI 2023, VIS 2022, CHI 2022, CSCW 2021, VIS 2021.

Leadership & Activities

January 2019 - May 2020 Student Ambassador
Georgia Institute of Technology Alumni Association
Serve as official representative of the Institute at events/tours for alumni, prospective students, and special guests.

January 2018 - May 2019 Executive Board Member -- Threads Co-chair
Stamps Scholars National Convention 2019
Executive board member of Stamps Scholars National Convention, a 3-day conference with over 700 student attendees. Responsible for 20-person committee that plans and coordinates the different content threads of the convention.

Skills

Programing Languages: Python (Advanced), Javascript/Typescript (Advanced), SQL (Intermediate)
Toolkits, Frameworks, Software: Svelte, React, Pytorch, Scikit-learn, Git, VegaLite, D3
Natural Languages: English (Native), Spanish (Advanced)