Steering Machine Learning Ecosystems of Interacting Agents

Zoom link for remote attendees

PW: 123123

Abstract: Modern machine learning models—such as LLMs and recommender systems—interact with humans, companies, and other models in a broader ecosystem. However, these multi-agent interactions often induce unintended ecosystem-level outcomes such as clickbait in classical content recommendation ecosystems, and more recently, safety violations and market concentration in nascent LLM ecosystems.

In this talk, I discuss my research on characterizing and steering ecosystem-level outcomes. I take an economic and statistical perspective on ML ecosystems, tracing outcomes back to the incentives of interacting agents and to the ML pipeline for training models. First, in LLM ecosystems, we show how analyzing a single model in isolation fails to capture ecosystem-level performance trends: for example, training a model with more resources can counterintuitively hurt ecosystem-level performance. To help steer ecosystem-level outcomes, we develop technical tools to assess how proposed policy interventions affect market entry, safety compliance, and user welfare. Then, turning to content recommendation ecosystems, we characterize a feedback loop between the recommender system and content creators, which shapes the diversity and quality of the content supply. Finally, I present a broader vision of ML ecosystems where multi-agent interactions are steered towards the desired algorithmic, market, and societal outcomes.

Bio: Meena Jagadeesan is a 5th year PhD student in Computer Science at UC Berkeley, where she is advised by Michael I. Jordan and Jacob Steinhardt. Her research investigates multi-agent interactions in machine learning ecosystems from an economic and statistical perspective. She has received an Open Philanthropy AI Fellowship and a Paul and Daisy Soros Fellowship.