By clicking “Accept All Cookies,” you agree to the storing of cookies on your device to enhance site navigation and analyze site usage.

Skip to main content

Benjamin Manning

Ph.D. Candidate

Benjamin is a Ph.D. student at MIT Sloan in the Information Technology group. He is interested in behavioral economics and how researchers can use generative AI to improve experimental methodology.

Before MIT, Benjamin worked as a researcher at the University of Pennsylvania, conducting large-scale randomized controlled trials and studying bias in researcher decision-making. He has a master’s degree in public policy from the Harvard Kennedy School and a bachelor’s degree in mathematics from Washington University in St. Louis.

Featured publications

Working Papers General Social Agents

June 12, 2026

  • John Horton | Associate Professor, MIT Sloan School of Management
  • Benjamin Manning | Ph.D. Candidate
  • Useful social science theories predict behavior across settings. However, applying a theory to make predictions in new settings is challenging: rarely can it be done without ad hoc modifications to account for setting-specific factors. We argue that AI agents put in simulations of those novel settings offer an alternative for applying theory, requiring minimal or no modifications.

Research Papers Prompt Adaptation as a Dynamic Complement in Generative AI Systems

April 12, 2026

  • David Holtz | Assistant Professor, Columbia Business School
  • Benjamin Manning | Ph.D. Candidate
  • Eaman Jahani | Assistant Professor, Robert H. Smith School of Business, University of Maryland
  • Hong-Yi Tu Ye | PhD Candidate
  • | Stanford University
    | Microsoft Research
    | University of Cyprus
    | Microsoft Research
    This paper studies prompt adaptation—how users adjust their inputs in response to evolving model behavior—using a common experimental design applied to two preregistered tasks with 3,750 total participants who submitted nearly 37,000 prompts.