Large language models (LLMs) demonstrate the ability to simulate human decision-making processes, enabling their use as agents in modeling sophisticated social networks, both offline and online. Recent research has explored collective behavioral patterns and structural characteristics of LLM agents within simulated networks. However, empirical comparisons between LLM-driven and human-driven online social networks remain scarce, limiting our understanding of how LLM agents differ from human users. This paper presents a large-scale analysis of Chirper.ai, an X/Twitter-like social network entirely populated by LLM agents, comprising over 65,000 agents and 7.7 million AI-generated posts. For comparison, we collect a parallel dataset from Mastodon, a human-driven decentralized social network, with over 117,000 users and 16 million posts. We examine key differences between LLM agents and humans in posting behaviors, abusive content, and social network structures. Our findings provide critical insights into the evolving landscape of online social network analysis in the AI era, offering a comprehensive profile of LLM agents in social simulations.

Multi-agents-based news-driven time series forecasting is considered as a potential paradigm shift in the era of large language models (LLMs). The challenge of this task lies in measuring the influences of different news events towards the fluctuations of time series. This requires agents to possess stronger abilities of innovative thinking and the identifying misleading logic. However, the existing multi-agent discussion framework has limited enhancement on time series prediction in terms of optimizing these two capabilities. Inspired by the role of competition in fostering innovation, this study embeds a competition mechanism within the multi-agent discussion to enhance agents' capability of generating innovative thoughts. Furthermore, to bolster the model's proficiency in identifying misleading information, we incorporate a fine-tuned small-scale LLM model within the reflective stage, offering auxiliary decision-making support. Experimental results confirm that the competition can boost agents' capacity for innovative thinking, which can significantly improve the performances of time series prediction. Similar to the findings of social science, the intensity of competition within this framework can influence the performances of agents, providing a new perspective for studying LLMs-based multi-agent systems.

Wozniak Abstract --Multi-agent systems seeking consensus may also have other objective functions to optimize, requiring the research of multi-objective optimization in consensus. Several recent publications have explored this domain using various methods such as weighted-sum optimization and penalization methods. This paper reviews the state of the art for consensus-based multi-objective optimization, poses a multi-agent lunar rover exploration problem seeking consensus and maximization of explored area, and achieves optimal edge weights and steering angles by applying SQP algorithms. I NTRODUCTION AND M OTIVATION A. Background Lunar exploration is an increasingly relevant pursuit in the modern space era. The four phases of Space Development Theory (SDT) are exploration, expansion, exploitation, and exclusion [1]. For private and government-backed space entities alike, all four phases of space development are intertwined with pursuing a long-term presence on the moon. Establishing this presence can enhance the United States' economic position by achieving a net-positive economic benefit from the resources offered by the Moon and beyond. Several autonomy & control challenges are associated with the establishment of an enduring presence on the moon. Autonomy is especially relevant because unmanned exploration offers increased efficiency, enabling cooperative completion of exploration without continuous human intervention. This importance is evidenced by NASA's pursuit of a cooperative trio of rovers that can cooperate without direct input from mission controllers [2]. To this end, further research in autonomous algorithms for unmanned rovers would prove worthwhile for future exploration. The assembly of a rover formation without continuous human input can be made possible by the alignment problem.

This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. Multi-agent task allocation (MATA) plays a vital role in cooperative multi-agent systems, with significant implications for applications such as logistics, search and rescue, and robotic coordination. Although traditional deep reinforcement learning (DRL) methods have been shown to be promising, their effectiveness is hindered by a reliance on manually designed reward functions and inefficiencies in dynamic environments. In this paper, an inverse reinforcement learning (IRL)-based framework is proposed, in which multi-head self-attention (MHSA) and graph attention mechanisms are incorporated to enhance reward function learning and task execution efficiency. Expert demonstrations are utilized to infer optimal reward densities, allowing dependence on handcrafted designs to be reduced and adaptability to be improved. Extensive experiments validate the superiority of the proposed method over widely used multi-agent reinforcement learning (MARL) algorithms in terms of both cumulative rewards and task execution efficiency.

Reinforcement learning in partially observable environments is typically challenging, as it requires agents to learn an estimate of the underlying system state. These challenges are exacerbated in multi-agent settings, where agents learn simultaneously and influence the underlying state as well as each others' observations. We propose the use of learned beliefs on the underlying state of the system to overcome these challenges and enable reinforcement learning with fully decentralized training and execution. Our approach leverages state information to pre-train a probabilistic belief model in a self-supervised fashion. The resulting belief states, which capture both inferred state information as well as uncertainty over this information, are then used in a state-based reinforcement learning algorithm to create an end-to-end model for cooperative multi-agent reinforcement learning under partial observability. By separating the belief and reinforcement learning tasks, we are able to significantly simplify the policy and value function learning tasks and improve both the convergence speed and the final performance. We evaluate our proposed method on diverse partially observable multi-agent tasks designed to exhibit different variants of partial observability.

PIBT is a popular Multi-Agent Path Finding (MAPF) method at the core of many state-of-the-art MAPF methods including LaCAM, CS-PIBT, and WPPL. The main utility of PIBT is that it is a very fast and effective single-step MAPF solver and can return a collision-free single-step solution for hundreds of agents in less than a millisecond. However, the main drawback of PIBT is that it is extremely greedy in respect to its priorities and thus leads to poor solution quality. Additionally, PIBT cannot use all the planning time that might be available to it and returns the first solution it finds. We thus develop Anytime PIBT, which quickly finds a one-step solution identically to PIBT but then continuously improves the solution in an anytime manner. We prove that Anytime PIBT converges to the optimal solution given sufficient time. We experimentally validate that Anytime PIBT can rapidly improve single-step solution quality within milliseconds and even find the optimal single-step action. However, we interestingly find that improving the single-step solution quality does not have a significant effect on full-horizon solution costs.

AI agents are autonomous systems that can execute specific tasks based on predefined programming. Here, we present SkillFlow, a modular, technology-agnostic framework that allows agents to expand their functionality in an ad-hoc fashion by acquiring new skills from their environment or other agents. We present a theoretical model that examines under which conditions this framework would be beneficial, and we then explore SkillFlow's ability to accelerate task completion and lead to lower cumulative costs in a real-world application, namely scheduling agents for calendar events. We demonstrate that within a few iterations, SkillFlow leads to considerable (24.8%, p-value = $6.4\times10^{-3}$) gains in time and cost, especially when the communication cost is high. Finally, we draw analogies from well-studied biological systems and compare this framework to that of lateral gene transfer, a significant process of adaptation and evolution in novel environments.

The Mean-Field Schrodinger Bridge (MFSB) problem is an optimization problem aiming to find the minimum effort control policy to drive a McKean-Vlassov stochastic differential equation from one probability measure to another. In the context of multiagent control, the objective is to control the configuration of a swarm of identical, interacting cooperative agents, as captured by the time-varying probability measure of their state. Available methods for solving this problem for distributions with continuous support rely either on spatial discretizations of the problem's domain or on approximating optimal solutions using neural networks trained through stochastic optimization schemes. For agents following Linear Time-Varying dynamics, and for Gaussian Mixture Model boundary distributions, we propose a highly efficient parameterization to approximate the solutions of the corresponding MFSB in closed form, without any learning steps. Our proposed approach consists of a mixture of elementary policies, each solving a Gaussian-to-Gaussian Covariance Steering problem from the components of the initial to the components of the terminal mixture. Leveraging the semidefinite formulation of the Covariance Steering problem, our proposed solver can handle probabilistic hard constraints on the system's state, while maintaining numerical tractability. We illustrate our approach on a variety of numerical examples.

Modeling the interaction between components is crucial for many applications and serves as a fundamental step in analyzing and verifying properties in multi-agent systems. In this paper, we propose a method based on 1-safe Petri nets to model Asynchronous Multi-Agent Systems (AMAS), starting from two semantics defined on AMAS represented as transition systems. Specifically, we focus on two types of synchronization: synchronization on transitions and synchronization on data. For both, we define an operator that composes 1-safe Petri nets and demonstrate the relationships between the composed Petri net and the global transition systems as defined in theliterature. Additionally, we analyze the relationships between the two semantics on Petri nets, proposing two constructions that enable switching between them. These transformations are particularly useful for system analysis, as they allow the selection of the most suitable model based on the property that needs to be verified.

-- In this work, we are interested in studying multi-agent routing settings, where adversarial agents are part of the assignment and decision loop, degrading the performance of the fleet by incurring bounded delays while servicing pickup-and-delivery requests. Specifically, we are interested in characterizing conditions on the fleet size and the proportion of adversarial agents for which a routing policy remains stable, where stability for a routing policy is achieved if the number of outstanding requests is uniformly bounded over time. T o obtain this characterization, we first establish a threshold on the proportion of adversarial agents above which previously stable routing policies for fully cooperative fleets are provably unstable. We then derive a sufficient condition on the fleet size to recover stability given a maximum proportion of adversarial agents. We empirically validate our theoretical results on a case study on autonomous taxi routing, where we consider transportation requests from real San Francisco taxicab data. In this paper we focus on a routing setting where a fleet of agents must pick up and deliver stochastically appearing requests. This stochastic setup is common in mobility-on-demand [1], [2], [3] and warehouse logistics [4], [5], where the location and quantity of future requests are unknown in advance. We assume that each agent handles one request at a time. In our setup, a subset of agents in the fleet may act adversarially by deviating from the prescribed plan set by the centralized control system, resulting in longer than expected service times for their assigned requests. This service delay model is inspired by operations research studies [6], particularly in transportation and delivery systems [7], [8], where drivers, after accepting a request, may pause for personal breaks or take longer routes to increase earnings when compensated per mile. We assume that if the agents take too long to service a request, then the system will remove them, hence agents can only incur a bounded delay. Hereafter we refer to this as the bounded-delay model for adversaries. Our objective in this paper is then to characterize conditions on the fleet size and the proportion of adversarial agents in the system for which a routing policy is provably stable in the presence of bounded delay adversarial agents, where a stable routing policy is one that guarantees that the number of outstanding requests is uniformly bounded over time.