相关论文: Agreement and Statistical Efficiency in Bayesian P…

Memory-based meta-learning is a powerful technique to build agents that adapt fast to any task within a target distribution. A previous theoretical study has argued that this remarkable performance is because the meta-training protocol…

The development of AI agents based on large, open-domain language models (LLMs) has paved the way for the development of general-purpose AI assistants that can support human in tasks such as writing, coding, graphic design, and scientific…

Following the Bayesian communication learning paradigm, we propose a finite population learning concept to capture the level of information aggregation in any given network, where agents are allowed to communicate with neighbors repeatedly…

We develop a novel framework of bounded rationality under cognitive frictions that studies learning over optimal behavior through both deliberative reasoning and accumulated experiences. Using both types of information, agents engage in…

Recent advancements in Large Language Models (LLMs) have enabled the emergence of multi-agent systems where LLMs interact, collaborate, and make decisions in shared environments. While individual model behavior has been extensively studied,…

Large language models (LLMs) demonstrate the capacity to reconstruct and trace learned content from their training data under specific elicitation conditions, yet this capability does not manifest in standard generation contexts. This…

A potential concern when simulating populations of large language models (LLMs) is data contamination, i.e. the possibility that training data may shape outcomes in unintended ways. While this concern is important and may hinder certain…

We consider a model of Bayesian observational learning in which a sequence of agents receives a private signal about an underlying binary state of the world. Each agent makes a decision based on its own signal and its observations of…

We introduce and study the problem of detecting whether an agent is updating their prior beliefs given new evidence in an optimal way that is Bayesian, or whether they are biased towards their own prior. In our model, biased agents form…

The remarkable generalization performance of large-scale models has been challenging the conventional wisdom of the statistical learning theory. Although recent theoretical studies have shed light on this behavior in linear models and…

In this paper, we settle the problem of learning optimal linear contracts from data in the offline setting, where agent types are drawn from an unknown distribution and the principal's goal is to design a contract that maximizes her…

Recent advances in Bayesian reinforcement learning (BRL) have shown that Bayes-optimality is theoretically achievable by modeling the environment's latent dynamics using Flat-Dirichlet-Multinomial (FDM) prior. In self-interested multi-agent…

Persuasion, a fundamental social capability for humans, remains a challenge for AI systems such as large language models (LLMs). Current studies often overlook the strategic use of information asymmetry in message design or rely on strong…

Large language models (LLMs) have demonstrated unprecedented emergent capabilities, including content generation, translation, and simulation of human behavior. Field experiments, on the other hand, are widely employed in social studies to…

Humans act via a nuanced process that depends both on rational deliberation and also on identity and contextual factors. In this work, we study how large language models (LLMs) can simulate human action in the context of social dilemma…

While a multi-agent approach based on large language models (LLMs) represents a promising strategy to surpass the capabilities of single models, its success is critically dependent on synergistic team composition. However, forming optimal…

Language models (LMs) are trained on collections of documents, written by individual human agents to achieve specific goals in an outside world. During training, LMs have access only to text of these documents, with no direct evidence of…

Multilevel models (MLMs) are a central building block of the Bayesian workflow. They enable joint, interpretable modeling of data across hierarchical levels and provide a fully probabilistic quantification of uncertainty. Despite their…

Previous work has showcased the intriguing capabilities of Large Language Models (LLMs) in instruction-following and rhetorical fluency. However, systematic exploration of their dual capabilities to autonomously persuade and resist…

Large Language Models (LLMs) have revolutionized Natural Language Processing but exhibit limitations, particularly in autonomously addressing novel challenges such as reasoning and problem-solving. Traditional techniques like…