Simulating strategic interactions with AI agents
TL;DR
This article introduces a framework for designing and running simulated experiments with LLM‐powered agents and applies the framework to the exploration–exploitation dilemma and shows that LLM‐based experiments reproduce patterns observed among human participants.
Abstract
We explore how Large Language Models (LLMs) can serve as synthetic subjects to inform strategy research. We introduce a framework for designing and running simulated experiments with LLM‐powered agents. We argue that this approach is useful for rapid, low‐cost prototyping of human experiments and for generating novel hypotheses. We apply the framework to the exploration–exploitation dilemma and show that LLM‐based experiments reproduce patterns observed among human participants. We then vary parameters and boundary conditions to illustrate how the same setup can support design iteration and surface hypotheses about when and why established results change. In the conclusion, we discuss the promise and limitations of artificial intelligence agents as “model organisms” for strategy. Artificial intelligence (AI) agents are beginning to enter firms as tools that can execute work, from writing code to coordinating complex tasks across systems. This article argues that their value for strategy extends beyond task automation: AI agents can also be used to simulate strategic interactions and assess how strategies perform under alternative assumptions. In our exploration–exploitation application, these simulations reproduce core patterns from prior human experiments and reveal where those patterns weaken or reverse. Used this way, AI agents can help firms prototype strategic choices, stress‐test assumptions, and direct managerial attention toward promising leads before larger commitments of time and effort.