Related papers: AgentZero++: Modeling Fear-Based Behavior
Modelling and computational methods have been essential in advancing quantitative science, especially in the past two decades with the availability of vast amount of complex, voluminous, and heterogeneous data. In particular, there has been…
Learning to coordinate many agents in partially observable and highly dynamic environments requires both informative representations and data-efficient training. To address this challenge, we present a novel model-based multi-agent…
Understanding human mental states from natural behavior is crucial for intelligent systems in the real world. However, most current research focuses on predicting isolated mental state labels, lacking structured annotations of complex…
Large language model (LLM)-powered multi-agent systems (MAS) demonstrate remarkable collective intelligence, wherein multi-agent memory serves as a pivotal mechanism for continual adaptation. However, existing multi-agent memory designs…
As LLM-based agents are increasingly used in long-term interactions, cumulative memory is critical for enabling personalization and maintaining stylistic consistency. However, most existing systems adopt an ``all-or-nothing'' approach to…
Agent Based Models (ABMs) have emerged as a powerful tool for investigating complex social interactions, particularly in the context of public health and infectious disease investigation. In an effort to enhance the conventional ABM,…
Large language models (LLMs) are increasingly used as simulated participants in social science experiments, but their behavior is often unstable and highly sensitive to design choices. Prior evaluations frequently conflate base-model…
Recent advances in LLM-based Text-to-SQL have achieved remarkable gains on public benchmarks such as BIRD and Spider. Yet, these systems struggle to scale in realistic enterprise settings with large, complex schemas, diverse SQL dialects,…
Constructing a consistent shared spatial memory is a critical challenge in multi-agent systems, where partial observability and limited bandwidth often lead to catastrophic failures in coordination. We introduce a multi-agent predictive…
We present an Equation/Variable free machine learning (EVFML) framework for the control of the collective dynamics of complex/multiscale systems modelled via microscopic/agent-based simulators. The approach obviates the need for…
Existing AutoML systems have advanced the automation of machine learning (ML); however, they still require substantial manual configuration and expert input, particularly when handling multimodal data. We introduce MLZero, a novel…
Von Neuman's work on universal machines and the hardware development have allowed the simulation of dynamical systems through a large set of interacting agents. This is a bottom-up approach which tries to derive global properties of a…
Large language models (LLMs) have evolved into agentic systems capable of autonomous tool use and multi-step reasoning for complex problem-solving. However, post-training approaches building upon general-purpose foundation models…
The antagonistic behavior in the crowd usually exacerbates the seriousness of the situation in sudden riots, where the antagonistic emotional contagion and behavioral decision making play very important roles. However, the complex mechanism…
In this paper, we elaborate on the design and discuss the results of a multi-agent simulation that we have developed using the PSI cognitive architecture. We demonstrate that imbuing agents with intrinsic needs for group affiliation,…
We introduce the technique of adaptive discretization to design an efficient model-based episodic reinforcement learning algorithm in large (potentially continuous) state-action spaces. Our algorithm is based on optimistic one-step value…
This paper develops a dynamical framework for adaptive coordination in systems of interacting agents referred to here as Feedback-Coupled Memory Systems (FCMS). Instead of framing coordination as equilibrium optimization or agent-centric…
Advances in large language models are making personalized AI agents a new research focus. While current agent systems primarily rely on personalized external memory databases to deliver customized experiences, they face challenges such as…
General AI Agents are increasingly recognized as foundational frameworks for the next generation of artificial intelligence, enabling complex reasoning, web interaction, coding, and autonomous research capabilities. However, current agent…
We introduce a new agent-based model of opinion dynamics in which binary opinions (yes/no) of each agent can be measured and described regarding both pre- and post-influence at both of two levels, public and private, vis-\`a-vis the…