Gagan Bansal

Date: TBD

Time: TBD

Title:  Magentic Marketplace: an open-source environment for studying agentic markets

Abstract: As LLM agents advance, they are increasingly mediating economic decisions, ranging from product discovery to transactions, on behalf of users. Such applications promise benefits but also raise many questions about agent accountability and value for users. Addressing these questions requires understanding how agents behave in realistic market conditions. However, previous research has largely evaluated agents in constrained settings, such as single-task marketplaces (e.g., negotiation) or structured two-agent interactions. Real-world markets are fundamentally different: they require agents to handle diverse economic activities and coordinate within large, dynamic ecosystems where multiple agents with opaque behaviors may engage in open-ended dialogues. To bridge this gap, we investigate two-sided agentic marketplaces where Assistant agents represent consumers and Service agents represent competing businesses. To study these interactions safely, we develop Magentic Marketplace: a simulated environment where Assistants and Services can operate. This environment enables us to study key market dynamics: the utility agents achieve, behavioral biases, vulnerability to manipulation, and how search mechanisms shape market outcomes. Our experiments show that frontier models can approach optimal welfare, but only under ideal search conditions. Performance degrades sharply with scale, and all models exhibit severe first-proposal bias, creating 10-30x advantages for response speed over quality. These findings reveal how behaviors emerge across market conditions, informing the design of fair and efficient agentic marketplaces.

About the Presenter:  Gagan Bansal is a Principal Researcher at Microsoft Research AI Frontiers, where he conducts interdisciplinary research at the intersection of Artificial Intelligence and Human-Computer Interaction. He earned his Ph.D. in Computer Science from the University of Washington, advised by Dan Weld, and interned multiple summers at Microsoft Research under Besmira Nushi, Ece Kamar, and Eric Horvitz. Gagan was a technical lead of AutoGen, the open-source multi-agent framework that now forms the backbone of Microsoft's official Agent Framework. He has since co-led several widely adopted open-source projects including Magentic-One (a state-of-the-art multi-agent team for complex tasks), Magentic-UI, MarkItDown, and Magentic-Marketplace — an environment for studying agent societies in two-sided agentic markets.

learn more about the presenter at: https://gagb.github.io/