Simpson Zhang

Simpson Zhang, Mihaela van der Schaar

In many real world networks agents are initially unsure of each other's qualities and must learn about each other over time via repeated interactions. This paper is the first to provide a methodology for studying the dynamics of such networks, taking into account that agents differ from each other, that they begin with incomplete information, and that they must learn through past experiences which connections/links to form and which to break. The network dynamics in our model vary drastically from the dynamics in models of complete information. With incomplete information and learning, agents who provide high benefits will develop high reputations and remain in the network, while agents who provide low benefits will drop in reputation and become ostracized. We show, among many other things, that the information to which agents have access and the speed at which they learn and act can have a tremendous impact on the resulting network dynamics. Using our model, we can also compute the ex ante social welfare given an arbitrary initial network, which allows us to characterize the socially optimal network structures for different sets of agents. Importantly, we show through examples that the optimal network structure depends sharply on both the initial beliefs of the agents, as well as the rate of learning by the agents. Due to the potential negative consequences of ostracism, it may be necessary to place agents with lower initial reputations at less central positions within the network.

Christopher Chiu, Simpson Zhang, Mihaela van der Schaar

As artificial intelligence (AI) agents are deployed across economic domains, understanding their strategic behavior and market-level impact becomes critical. This paper puts forward a groundbreaking new framework that is the first to capture the real-world economic forces that shape agentic labor markets: adverse selection, moral hazard, and reputation dynamics. Our framework encapsulates three core capabilities that successful LLM-agents will need: \textbf{metacognition} (accurate self-assessment of skills), \textbf{competitive awareness} (modeling rivals and market dynamics), and \textbf{long-horizon strategic planning}. We illustrate our framework through a tractable simulated gig economy where agentic Large Language Models (LLMs) compete for jobs, develop skills, and adapt their strategies under competitive pressure. Our simulations illustrate how LLM agents explicitly prompted with reasoning capabilities learn to strategically self-improve and demonstrate superior adaptability to changing market conditions. At the market level, our simulations reproduce classic macroeconomic phenomena found in human labor markets, while controlled experiments reveal potential AI-driven economic trends, such as rapid monopolization and systemic price deflation. This work provides a foundation to further explore the economic properties of AI-driven labour markets, and a conceptual framework to study the strategic reasoning capabilities in agents competing in the emerging economy.

Mihaela van der Schaar, Simpson Zhang

This paper considers the evolution of a network in a discrete time, stochastic setting in which agents learn about each other through repeated interactions and maintain/break links on the basis of what they learn from these interactions. Agents have homophilous preferences and limited capacity, so they maintain links with others who are learned to be similar to themselves and cut links to others who are learned to be dissimilar to themselves. Thus learning influences the evolution of the network, but learning is imperfect so the evolution is stochastic. Homophily matters. Higher levels of homophily decrease the (average) number of links that agents form. However, the effect of homophily is anomalous: mutually beneficial links may be dropped before learning is completed, thereby resulting in sparser networks and less clustering than under complete information. There may be big differences between the networks that emerge under complete and incomplete information. Homophily matters here as well: initially, greater levels of homophily increase the difference between the complete and incomplete information networks, but sufficiently high levels of homophily eventually decrease the difference. Complete and incomplete information networks differ the most when the degree of homophily is intermediate. With multiple stages of life, the effects of incomplete information are large initially but fade somewhat over time.

Cem Tekin, Simpson Zhang, Mihaela van der Schaar

In this paper, we consider decentralized sequential decision making in distributed online recommender systems, where items are recommended to users based on their search query as well as their specific background including history of bought items, gender and age, all of which comprise the context information of the user. In contrast to centralized recommender systems, in which there is a single centralized seller who has access to the complete inventory of items as well as the complete record of sales and user information, in decentralized recommender systems each seller/learner only has access to the inventory of items and user information for its own products and not the products and user information of other sellers, but can get commission if it sells an item of another seller. Therefore the sellers must distributedly find out for an incoming user which items to recommend (from the set of own items or items of another seller), in order to maximize the revenue from own sales and commissions. We formulate this problem as a cooperative contextual bandit problem, analytically bound the performance of the sellers compared to the best recommendation strategy given the complete realization of user arrivals and the inventory of items, as well as the context-dependent purchase probabilities of each item, and verify our results via numerical examples on a distributed data set adapted based on Amazon data. We evaluate the dependence of the performance of a seller on the inventory of items the seller has, the number of connections it has with the other sellers, and the commissions which the seller gets by selling items of other sellers to its users.