-
V2AIX: A Multi-Modal Real-World Dataset of ETSI ITS V2X Messages in Public Road Traffic arXiv.cs.MA Pub Date : 2024-03-15 Guido Kueppers, Jean-Pierre Busch, Lennart Reiher, Lutz Eckstein
Connectivity is a main driver for the ongoing megatrend of automated mobility: future Cooperative Intelligent Transport Systems (C-ITS) will connect road vehicles, traffic signals, roadside infrastructure, and even vulnerable road users, sharing data and compute for safer, more efficient, and more comfortable mobility. In terms of communication technology for realizing such vehicle-to-everything (V2X)
-
What Makes Good Collaborative Views? Contrastive Mutual Information Maximization for Multi-Agent Perception arXiv.cs.MA Pub Date : 2024-03-15 Wanfang Su, Lixing Chen, Yang Bai, Xi Lin, Gaolei Li, Zhe Qu, Pan Zhou
Multi-agent perception (MAP) allows autonomous systems to understand complex environments by interpreting data from multiple sources. This paper investigates intermediate collaboration for MAP with a specific focus on exploring "good" properties of collaborative view (i.e., post-collaboration feature) and its underlying relationship to individual views (i.e., pre-collaboration features), which were
-
Multi-Objective Optimization Using Adaptive Distributed Reinforcement Learning arXiv.cs.MA Pub Date : 2024-03-13 Jing Tan, Ramin Khalili, Holger Karl
The Intelligent Transportation System (ITS) environment is known to be dynamic and distributed, where participants (vehicle users, operators, etc.) have multiple, changing and possibly conflicting objectives. Although Reinforcement Learning (RL) algorithms are commonly applied to optimize ITS applications such as resource management and offloading, most RL algorithms focus on single objectives. In
-
An Algorithmic Theory of Simplicity in Mechanism Design arXiv.cs.MA Pub Date : 2024-03-13 Diodato Ferraioli, Carmine Ventre
A growing body of work in economics and computation focuses on the trade-off between implementability and simplicity in mechanism design. The goal is to develop a theory that not only allows to design an incentive structure easy to grasp for imperfectly rational agents, but also understand the ensuing limitations on the class of mechanisms that enforce it. In this context, the concept of OSP mechanisms
-
CleanAgent: Automating Data Standardization with LLM-based Agents arXiv.cs.MA Pub Date : 2024-03-13 Danrui Qi, Jiannan Wang
Data standardization is a crucial part in data science life cycle. While tools like Pandas offer robust functionalities, their complexity and the manual effort required for customizing code to diverse column types pose significant challenges. Although large language models (LLMs) like ChatGPT have shown promise in automating this process through natural language understanding and code generation, it
-
Ariadne and Theseus: Exploration and Rendezvous with Two Mobile Agents in an Unknown Graph arXiv.cs.MA Pub Date : 2024-03-12 Romain Cosson
We investigate two fundamental problems in mobile computing: exploration and rendezvous, with two distinct mobile agents in an unknown graph. The agents can read and write information on whiteboards that are located at all nodes. They both move along one adjacent edge at every time-step. In the exploration problem, both agents start from the same node of the graph and must traverse all of its edges
-
Transforming Competition into Collaboration: The Revolutionary Role of Multi-Agent Systems and Language Models in Modern Organizations arXiv.cs.MA Pub Date : 2024-03-12 Carlos Jose Xavier Cruz
This article explores the dynamic influence of computational entities based on multi-agent systems theory (SMA) combined with large language models (LLM), which are characterized by their ability to simulate complex human interactions, as a possibility to revolutionize human user interaction from the use of specialized artificial agents to support everything from operational organizational processes
-
Bigraph Matching Weighted with Learnt Incentive Function for Multi-Robot Task Allocation arXiv.cs.MA Pub Date : 2024-03-11 Steve Paul, Nathan Maurer, Souma Chowdhury
Most real-world Multi-Robot Task Allocation (MRTA) problems require fast and efficient decision-making, which is often achieved using heuristics-aided methods such as genetic algorithms, auction-based methods, and bipartite graph matching methods. These methods often assume a form that lends better explainability compared to an end-to-end (learnt) neural network based policy for MRTA. However, deriving
-
Multi-Agent Reinforcement Learning with a Hierarchy of Reward Machines arXiv.cs.MA Pub Date : 2024-03-08 Xuejing Zheng, Chao Yu
In this paper, we study the cooperative Multi-Agent Reinforcement Learning (MARL) problems using Reward Machines (RMs) to specify the reward functions such that the prior knowledge of high-level events in a task can be leveraged to facilitate the learning efficiency. Unlike the existing work that RMs have been incorporated into MARL for task decomposition and policy learning in relatively simple domains
-
The Geometry of Cyclical Social Trends arXiv.cs.MA Pub Date : 2024-03-11 Bernard Chazelle, Kritkorn Karntikoon, Jakob Nogler
We investigate the emergence of periodic behavior in opinion dynamics and its underlying geometry. For this, we use a bounded-confidence model with contrarian agents in a convolution social network. This means that agents adapt their opinions by interacting with their neighbors in a time-varying social network. Being contrarian, the agents are kept from reaching consensus. This is the key feature that
-
IDEAS: Information-Driven EV Admission in Charging Station Considering User Impatience to Improve QoS and Station Utilization arXiv.cs.MA Pub Date : 2024-03-10 Animesh Chattopadhyay, Subrat Kar
Our work delves into user behaviour at Electric Vehicle(EV) charging stations during peak times, particularly focusing on how impatience drives balking (not joining queues) and reneging (leaving queues prematurely). We introduce an Agent-based simulation framework that incorporates user optimism levels (pessimistic, standard, and optimistic) in the queue dynamics. Unlike previous work, this framework
-
Invariant Properties of Linear-Iterative Distributed Averaging Algorithms and Application to Error Detection arXiv.cs.MA Pub Date : 2024-03-09 Christoforos N. Hadjicostis, Alejandro D. Dominguez-Garcia
We consider the problem of average consensus in a distributed system comprising a set of nodes that can exchange information among themselves. We focus on a class of algorithms for solving such a problem whereby each node maintains a state and updates it iteratively as a linear combination of the states maintained by its in-neighbors, i.e., nodes from which it receives information directly. Averaging
-
Decentralized and Lifelong-Adaptive Multi-Agent Collaborative Learning arXiv.cs.MA Pub Date : 2024-03-11 Shuo Tang, Rui Ye, Chenxin Xu, Xiaowen Dong, Siheng Chen, Yanfeng Wang
Decentralized and lifelong-adaptive multi-agent collaborative learning aims to enhance collaboration among multiple agents without a central server, with each agent solving varied tasks over time. To achieve efficient collaboration, agents should: i) autonomously identify beneficial collaborative relationships in a decentralized manner; and ii) adapt to dynamically changing task observations. In this
-
Engineering consensus in static networks with unknown disruptors arXiv.cs.MA Pub Date : 2024-03-08 Agathe Bouis, Christopher Lowe, Ruaridh A. Clark, Malcolm Macdonald
Distributed control increases system scalability, flexibility, and redundancy. Foundational to such decentralisation is consensus formation, by which decision-making and coordination are achieved. However, decentralised multi-agent systems are inherently vulnerable to disruption. To develop a resilient consensus approach, inspiration is taken from the study of social systems and their dynamics; specifically
-
Distributed Multi-objective Optimization in Cyber-Physical Energy Systems arXiv.cs.MA Pub Date : 2024-03-07 Sanja Stark, Emilie Frost, Marvin Nebel-Wenner
Managing complex Cyber-Physical Energy Systems (CPES) requires solving various optimization problems with multiple objectives and constraints. As distributed control architectures are becoming more popular in CPES for certain tasks due to their flexibility, robustness, and privacy protection, multi-objective optimization must also be distributed. For this purpose, we present MO-COHDA, a fully distributed
-
Cooperative Task Execution in Multi-Agent Systems arXiv.cs.MA Pub Date : 2024-03-07 Karishma, Shrisha Rao
We propose a multi-agent system that enables groups of agents to collaborate and work autonomously to execute tasks. Groups can work in a decentralized manner and can adapt to dynamic changes in the environment. Groups of agents solve assigned tasks by exploring the solution space cooperatively based on the highest reward first. The tasks have a dependency structure associated with them. We rigorously
-
A Multi-agent Reinforcement Learning Study of Evolution of Communication and Teaching under Libertarian and Utilitarian Governing Systems arXiv.cs.MA Pub Date : 2024-03-04 Aslan S. Dizaji
Laboratory experiments have shown that communication plays an important role in solving social dilemmas. Here, by extending the AI-Economist, a mixed motive multi-agent reinforcement learning environment, I intend to find an answer to the following descriptive question: which governing system does facilitate the emergence and evolution of communication and teaching among agents? To answer this question
-
KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents arXiv.cs.MA Pub Date : 2024-03-05 Yuqi Zhu, Shuofei Qiao, Yixin Ou, Shumin Deng, Ningyu Zhang, Shiwei Lyu, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen
Large Language Models (LLMs) have demonstrated great potential in complex reasoning tasks, yet they fall short when tackling more sophisticated challenges, especially when interacting with environments through generating executable actions. This inadequacy primarily stems from the lack of built-in action knowledge in language agents, which fails to effectively guide the planning trajectories during
-
Can Poverty Be Reduced by Acting on Discrimination? An Agent-based Model for Policy Making arXiv.cs.MA Pub Date : 2024-03-03 Alba Aguilera, Nieves Montes, Georgina Curto, Carles Sierra, Nardine Osman
In the last decades, there has been a deceleration in the rates of poverty reduction, suggesting that traditional redistributive approaches to poverty mitigation could be losing effectiveness, and alternative insights to advance the number one UN Sustainable Development Goal are required. The criminalization of poor people has been denounced by several NGOs, and an increasing number of voices suggest
-
Offline Fictitious Self-Play for Competitive Games arXiv.cs.MA Pub Date : 2024-02-29 Jingxiao Chen, Weiji Xie, Weinan Zhang, Yong yu, Ying Wen
Offline Reinforcement Learning (RL) has received significant interest due to its ability to improve policies in previously collected datasets without online interactions. Despite its success in the single-agent setting, offline multi-agent RL remains a challenge, especially in competitive games. Firstly, unaware of the game structure, it is impossible to interact with the opponents and conduct a major
-
Policy Space Response Oracles: A Survey arXiv.cs.MA Pub Date : 2024-03-04 Ariyan Bighashdel, Yongzhao Wang, Stephen McAleer, Rahul Savani, Frans A. Oliehoek
In game theory, a game refers to a model of interaction among rational decision-makers or players, making choices with the goal of achieving their individual objectives. Understanding their behavior in games is often referred to as game reasoning. This survey provides a comprehensive overview of a fast-developing game-reasoning framework for large games, known as Policy Space Response Oracles (PSRO)
-
Cognition is All You Need - The Next Layer of AI Above Large Language Models arXiv.cs.MA Pub Date : 2024-03-04 Nova Spivack, Sam Douglas, Michelle Crames, Tim Connors
Recent studies of the applications of conversational AI tools, such as chatbots powered by large language models, to complex real-world knowledge work have shown limitations related to reasoning and multi-step problem solving. Specifically, while existing chatbots simulate shallow reasoning and understanding they are prone to errors as problem complexity increases. The failure of these systems to address
-
SMAUG: A Sliding Multidimensional Task Window-Based MARL Framework for Adaptive Real-Time Subtask Recognition arXiv.cs.MA Pub Date : 2024-03-04 Wenjing Zhang, Wei Zhang
Instead of making behavioral decisions directly from the exponentially expanding joint observational-action space, subtask-based multi-agent reinforcement learning (MARL) methods enable agents to learn how to tackle different subtasks. Most existing subtask-based MARL methods are based on hierarchical reinforcement learning (HRL). However, these approaches often limit the number of subtasks, perform
-
Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning arXiv.cs.MA Pub Date : 2024-03-02 Hyungho Na, Yunkyeong Seo, Il-chul Moon
In cooperative multi-agent reinforcement learning (MARL), agents aim to achieve a common goal, such as defeating enemies or scoring a goal. Existing MARL algorithms are effective but still require significant learning time and often get trapped in local optima by complex tasks, subsequently failing to discover a goal-reaching policy. To address this, we introduce Efficient episodic Memory Utilization
-
Leveraging Team Correlation for Approximating Equilibrium in Two-Team Zero-Sum Games arXiv.cs.MA Pub Date : 2024-03-01 Naming Liu, Mingzhi Wang, Youzhi Zhang, Yaodong Yang, Bo An, Ying Wen
Two-team zero-sum games are one of the most important paradigms in game theory. In this paper, we focus on finding an unexploitable equilibrium in large team games. An unexploitable equilibrium is a worst-case policy, where members in the opponent team cannot increase their team reward by taking any policy, e.g., cooperatively changing to other joint policies. As an optimal unexploitable equilibrium
-
Efficient Reinforcement Learning for Global Decision Making in the Presence of Local Agents at Scale arXiv.cs.MA Pub Date : 2024-03-01 Emile Anand, Guannan Qu
We study reinforcement learning for global decision-making in the presence of many local agents, where the global decision-maker makes decisions affecting all local agents, and the objective is to learn a policy that maximizes the rewards of both the global and the local agents. Such problems find many applications, e.g. demand response, EV charging, queueing, etc. In this setting, scalability has
-
Understanding Iterative Combinatorial Auction Designs via Multi-Agent Reinforcement Learning arXiv.cs.MA Pub Date : 2024-02-29 Greg d'Eon, Neil Newman, Kevin Leyton-Brown
Iterative combinatorial auctions are widely used in high stakes settings such as spectrum auctions. Such auctions can be hard to understand analytically, making it difficult for bidders to determine how to behave and for designers to optimize auction rules to ensure desirable outcomes such as high revenue or welfare. In this paper, we investigate whether multi-agent reinforcement learning (MARL) algorithms
-
Imagine, Initialize, and Explore: An Effective Exploration Method in Multi-Agent Reinforcement Learning arXiv.cs.MA Pub Date : 2024-02-28 Zeyang Liu, Lipeng Wan, Xinrui Yang, Zhuoran Chen, Xingyu Chen, Xuguang Lan
Effective exploration is crucial to discovering optimal strategies for multi-agent reinforcement learning (MARL) in complex coordination tasks. Existing methods mainly utilize intrinsic rewards to enable committed exploration or use role-based learning for decomposing joint action spaces instead of directly conducting a collective search in the entire action-observation space. However, they often face
-
Independent Learning in Constrained Markov Potential Games arXiv.cs.MA Pub Date : 2024-02-27 Philip Jordan, Anas Barakat, Niao He
Constrained Markov games offer a formal mathematical framework for modeling multi-agent reinforcement learning problems where the behavior of the agents is subject to constraints. In this work, we focus on the recently introduced class of constrained Markov Potential Games. While centralized algorithms have been proposed for solving such constrained games, the design of converging independent learning
-
Large Language Model for Participatory Urban Planning arXiv.cs.MA Pub Date : 2024-02-27 Zhilun Zhou, Yuming Lin, Depeng Jin, Yong Li
Participatory urban planning is the mainstream of modern urban planning that involves the active engagement of residents. However, the traditional participatory paradigm requires experienced planning experts and is often time-consuming and costly. Fortunately, the emerging Large Language Models (LLMs) have shown considerable ability to simulate human-like agents, which can be used to emulate the participatory
-
Replicating Electoral Success arXiv.cs.MA Pub Date : 2024-02-27 Kiran Tomlinson, Tanvi Namjoshi, Johan Ugander, Jon Kleinberg
A core tension in the study of plurality elections is the clash between the classic Hotelling-Downs model, which predicts that two office-seeking candidates should position themselves at the median voter's policy, and the empirical observation that real-world democracies often have two major parties with divergent policies. Motivated by this tension and drawing from bounded rationality, we introduce
-
Navigating Complexity: Orchestrated Problem Solving with Multi-Agent LLMs arXiv.cs.MA Pub Date : 2024-02-26 Sumedh Rasal, E. J. Hauer
Large Language Models (LLMs) have demonstrated remarkable capabilities in solving various tasks, yet they often struggle with comprehensively addressing complex and vague problems. Existing approaches, including multi-agent LLM systems, offer solutions to certain challenges but still require manual setup and lack scalability. To address this gap, we propose a novel approach leveraging decomposition
-
Distributed Finite-time Differentiator for Multi-agent Systems Under Directed Graph arXiv.cs.MA Pub Date : 2024-02-26 Weile Chen, Haibo Du, Shihua Li
This paper proposes a new distributed finite-time differentiator (DFD) for multi-agent systems (MAS) under directed graph, which extends the differentiator algorithm from the centralized case to the distributed case by only using relative/absolute position information. By skillfully constructing a Lyapunov function, the finite-time stability of the closed-loop system under DFD is proved. Inspired by
-
AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System arXiv.cs.MA Pub Date : 2024-02-23 Zhiwei Liu, Weiran Yao, Jianguo Zhang, Liangwei Yang, Zuxin Liu, Juntao Tan, Prafulla K. Choubey, Tian Lan, Jason Wu, Huan Wang, Shelby Heinecke, Caiming Xiong, Silvio Savarese
The booming success of LLMs initiates rapid development in LLM agents. Though the foundation of an LLM agent is the generative model, it is critical to devise the optimal reasoning strategies and agent architectures. Accordingly, LLM agent research advances from the simple chain-of-thought prompting to more complex ReAct and Reflection reasoning strategy; agent architecture also evolves from single
-
Language Agents as Optimizable Graphs arXiv.cs.MA Pub Date : 2024-02-26 Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin, Jurgen Schmidhuber
Various human-designed prompt engineering techniques have been proposed to improve problem solvers based on Large Language Models (LLMs), yielding many disparate code bases. We unify these approaches by describing LLM-based agents as computational graphs. The nodes implement functions to process multimodal data or query LLMs, and the edges describe the information flow between operations. Graphs can
-
Learning Translations: Emergent Communication Pretraining for Cooperative Language Acquisition arXiv.cs.MA Pub Date : 2024-02-26 Dylan Cope, Peter McBurney
In Emergent Communication (EC) agents learn to communicate with one another, but the protocols that they develop are specialised to their training community. This observation led to research into Zero-Shot Coordination (ZSC) for learning communication strategies that are robust to agents not encountered during training. However, ZSC typically assumes that no prior data is available about the agents
-
Egalitarian Price of Fairness for Indivisible Goods arXiv.cs.MA Pub Date : 2024-02-25 Karen Frilya CelineNational University of Singapore, Muhammad Ayaz DzulfikarNational University of Singapore, Ivan Adrian KoswaraNational University of Singapore
In the context of fair division, the concept of price of fairness has been introduced to quantify the loss of welfare when we have to satisfy some fairness condition. In other words, it is the price we have to pay to guarantee fairness. Various settings of fair division have been considered previously; we extend to the setting of indivisible goods by using egalitarian welfare as the welfare measure
-
Cooperation and Control in Delegation Games arXiv.cs.MA Pub Date : 2024-02-24 Oliver Sourbut, Lewis Hammond, Harriet Wood
Many settings of interest involving humans and machines -- from virtual personal assistants to autonomous vehicles -- can naturally be modelled as principals (humans) delegating to agents (machines), which then interact with each other on their principals' behalf. We refer to these multi-principal, multi-agent scenarios as delegation games. In such games, there are two important failure modes: problems
-
Platforms for Efficient and Incentive-Aware Collaboration arXiv.cs.MA Pub Date : 2024-02-23 Nika Haghtalab, Mingda Qiao, Kunhe Yang
Collaboration is crucial for reaching collective goals. However, its effectiveness is often undermined by the strategic behavior of individual agents -- a fact that is captured by a high Price of Stability (PoS) in recent literature [Blum et al., 2021]. Implicit in the traditional PoS analysis is the assumption that agents have full knowledge of how their tasks relate to one another. We offer a new
-
A New Dynamic Distributed Planning Approach: Application to DPDP Problems arXiv.cs.MA Pub Date : 2024-02-24 Zakaria Tolba
In this work, we proposed a new dynamic distributed planning approach that is able to take into account the changes that the agent introduces on his set of actions to be planned in order to take into account the changes that occur in his environment. Our approach fits into the context of distributed planning for distributed plans where each agent can produce its own plans. According to our approach
-
A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health arXiv.cs.MA Pub Date : 2024-02-22 Nikhil Behari, Edwin Zhang, Yunfan Zhao, Aparna Taneja, Dheeraj Nagaraj, Milind Tambe
Efforts to reduce maternal mortality rate, a key UN Sustainable Development target (SDG Target 3.1), rely largely on preventative care programs to spread critical health information to high-risk populations. These programs face two important challenges: efficiently allocating limited health resources to large beneficiary populations, and adapting to evolving policy priorities. While prior works in
-
AgentScope: A Flexible yet Robust Multi-Agent Platform arXiv.cs.MA Pub Date : 2024-02-21 Dawei Gao, Zitao Li, Weirui Kuang, Xuchen Pan, Daoyuan Chen, Zhijian Ma, Bingchen Qian, Liuyi Yao, Lin Zhu, Chen Cheng, Hongzhu Shi, Yaliang Li, Bolin Ding, Jingren Zhou
With the rapid advancement of Large Language Models (LLMs), significant progress has been made in multi-agent applications. However, the complexities in coordinating agents' cooperation and LLMs' erratic performance pose notable challenges in developing robust and efficient multi-agent applications. To tackle these challenges, we propose AgentScope, a developer-centric multi-agent platform with message
-
Aligning Individual and Collective Objectives in Multi-Agent Cooperation arXiv.cs.MA Pub Date : 2024-02-19 Yang Li, Wenhao Zhang, Jianhong Wang, Shao Zhang, Yali Du, Ying Wen, Wei Pan
In the field of multi-agent learning, the challenge of mixed-motive cooperation is pronounced, given the inherent contradictions between individual and collective goals. Current research in this domain primarily focuses on incorporating domain knowledge into rewards or introducing additional mechanisms to foster cooperation. However, many of these methods suffer from the drawbacks of manual design
-
Navigating simplicity and complexity of social-ecological systems through a dialog between dynamical systems and agent-based models arXiv.cs.MA Pub Date : 2024-02-19 Sonja Radosavljevic, Udita Sanga, Maja Schlüter
Social-ecological systems (SES) research aims to understand the nature of social-ecological phenomena, to find effective ways to foster or manage conditions under which desirable phenomena, such as sustainable resource use, occur or to change conditions or reduce the negative consequences of undesirable phenomena, such as poverty traps. Challenges such as these are often addressed using dynamical systems
-
On the Limits of Information Spread by Memory-less Agents arXiv.cs.MA Pub Date : 2024-02-18 Niccolò D'ArchivioSapienza Università di Roma, Robin VacusBocconi University
We address the self-stabilizing bit-dissemination problem, designed to capture the challenges of spreading information and reaching consensus among entities with minimal cognitive and communication capacities. Specifically, a group of $n$ agents is required to adopt the correct opinion, initially held by a single informed individual, choosing from two possible opinions. In order to make decisions,
-
Online Physical Enhanced Residual Learning for Connected Autonomous Vehicles Platoon Centralized Control arXiv.cs.MA Pub Date : 2024-02-18 Hang Zhou, Heye Huang, Peng Zhang, Haotian Shi, Keke Long, Xiaopeng Li
This paper introduces an online physical enhanced residual learning (PERL) framework for Connected Autonomous Vehicles (CAVs) platoon, aimed at addressing the challenges posed by the dynamic and unpredictable nature of traffic environments. The proposed framework synergistically combines a physical model, represented by Model Predictive Control (MPC), with data-driven online Q-learning. The MPC controller
-
Adaptive Decision-Making for Autonomous Vehicles: A Learning-Enhanced Game-Theoretic Approach in Interactive Environments arXiv.cs.MA Pub Date : 2024-02-18 Heye Huang, Jinxin Liu, Guanya Shi, Shiyue Zhao, Boqi Li, Jianqiang Wang
This paper proposes an adaptive behavioral decision-making method for autonomous vehicles (AVs) focusing on complex merging scenarios. Leveraging principles from non-cooperative game theory, we develop a vehicle interaction behavior model that defines key traffic elements and integrates a multifactorial reward function. Maximum entropy inverse reinforcement learning (IRL) is employed for behavior model
-
Multi-Generative Agent Collective Decision-Making in Urban Planning: A Case Study for Kendall Square Renovation arXiv.cs.MA Pub Date : 2024-02-17 Jin Gao, Hanyong Xu, Luc Dao
In this study, we develop a multiple-generative agent system to simulate community decision-making for the redevelopment of Kendall Square's Volpe building. Drawing on interviews with local stakeholders, our simulations incorporated varying degrees of communication, demographic data, and life values in the agent prompts. The results revealed that communication among agents improved collective reasoning
-
LLM Agents for Psychology: A Study on Gamified Assessments arXiv.cs.MA Pub Date : 2024-02-19 Qisen Yang, Zekun Wang, Honghui Chen, Shenzhi Wang, Yifan Pu, Xin Gao, Wenhao Huang, Shiji Song, Gao Huang
Psychological measurement is essential for mental health, self-understanding, and personal development. Traditional methods, such as self-report scales and psychologist interviews, often face challenges with engagement and accessibility. While game-based and LLM-based tools have been explored to improve user interest and automate assessment, they struggle to balance engagement with generalizability
-
Easy as ABCs: Unifying Boltzmann Q-Learning and Counterfactual Regret Minimization arXiv.cs.MA Pub Date : 2024-02-19 Luca D'Amico-Wong, Hugh Zhang, Marc Lanctot, David C. Parkes
We propose ABCs (Adaptive Branching through Child stationarity), a best-of-both-worlds algorithm combining Boltzmann Q-learning (BQL), a classic reinforcement learning algorithm for single-agent domains, and counterfactual regret minimization (CFR), a central algorithm for learning in multi-agent domains. ABCs adaptively chooses what fraction of the environment to explore each iteration by measuring
-
Middleware-based multi-agent development environment for building and testing distributed intelligent systems arXiv.cs.MA Pub Date : 2024-02-14 Francisco José Aguayo-Canela, Héctor Alaiz-Moretón, María Teresa García-Ordás, José Alberto Benítez-Andrades, Carmen Benavides, Paulo Novais, Isaías García-Rodríguez
The spread of the Internet of Things (IoT) is demanding new, powerful architectures for handling the huge amounts of data produced by the IoT devices. In many scenarios, many existing isolated solutions applied to IoT devices use a set of rules to detect, report and mitigate malware activities or threats. This paper describes a development environment that allows the programming and debugging of such
-
Enriched multi-agent middleware for building rule-based distributed security solutions for IoT environments arXiv.cs.MA Pub Date : 2024-02-14 Francisco José Aguayo-Canela, Héctor Alaiz-Moretón, María Teresa García-Ordás, José Alberto Benítez-Andrades, Carmen Benavides, Isaías García-Rodríguez
The increasing number of connected devices and the complexity of Internet of Things (IoT) ecosystems are demanding new architectures for managing and securing these networked environments. Intrusion Detection Systems (IDS) are security solutions that help to detect and mitigate the threats that IoT systems face, but there is a need for new IDS strategies and architectures. This paper describes a development
-
OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models arXiv.cs.MA Pub Date : 2024-02-15 Ali AhmadiTeshnizi, Wenzhi Gao, Madeleine Udell
Optimization problems are pervasive in sectors from manufacturing and distribution to healthcare. However, most such problems are still solved heuristically by hand rather than optimally by state-of-the-art solvers because the expertise required to formulate and solve these problems limits the widespread adoption of optimization tools and techniques. This paper introduces OptiMUS, a Large Language
-
Identifying and modelling cognitive biases in mobility choices arXiv.cs.MA Pub Date : 2024-02-15 Chloe Conrad, Carole Adam
This report presents results from an M1 internship dedicated to agent-based modelling and simulation of daily mobility choices. This simulation is intended to be realistic enough to serve as a basis for a serious game about the mobility transition. In order to ensure this level of realism, we conducted a survey to measure if real mobility choices are made rationally, or how biased they are. Results
-
Strategic Vote Timing in Online Elections With Public Tallies arXiv.cs.MA Pub Date : 2024-02-15 Aviv Yaish, Svetlana Abramova, Rainer Böhme
We study the effect of public tallies on online elections, in a setting where voting is costly and voters are allowed to strategically time their votes. The strategic importance of choosing \emph{when} to vote arises when votes are public, such as in online event scheduling polls (e.\,g., Doodle), or in blockchain governance mechanisms. In particular, there is a tension between voting early to influence
-
Optimal Task Assignment and Path Planning using Conflict-Based Search with Precedence and Temporal Constraints arXiv.cs.MA Pub Date : 2024-02-13 Yu Quan Chong, Jiaoyang Li, Katia Sycara
The Multi-Agent Path Finding (MAPF) problem entails finding collision-free paths for a set of agents, guiding them from their start to goal locations. However, MAPF does not account for several practical task-related constraints. For example, agents may need to perform actions at goal locations with specific execution times, adhering to predetermined orders and timeframes. Moreover, goal assignments
-
Logic of Awareness for Nested Knowledge arXiv.cs.MA Pub Date : 2024-02-13 Yudai Kubono
Reasoning abilities of human beings are limited. Logics that treat logical inference for human knowledge should reflect these limited abilities. Logic of awareness is one of those logics. In the logic, what an agent with a limited reasoning ability actually knows at a given moment (explicit knowledge) is distinguished from the ideal knowledge that an agent obtains by performing all possible inferences
-
Conservative and Risk-Aware Offline Multi-Agent Reinforcement Learning for Digital Twins arXiv.cs.MA Pub Date : 2024-02-13 Eslam Eldeeb, Houssem Sifaou, Osvaldo Simeone, Mohammad Shehab, Hirley Alves
Digital twin (DT) platforms are increasingly regarded as a promising technology for controlling, optimizing, and monitoring complex engineering systems such as next-generation wireless networks. An important challenge in adopting DT solutions is their reliance on data collected offline, lacking direct access to the physical environment. This limitation is particularly severe in multi-agent systems
-
Learning Optimal Tax Design in Nonatomic Congestion Games arXiv.cs.MA Pub Date : 2024-02-12 Qiwen Cui, Maryam Fazel, Simon S. Du
We study how to learn the optimal tax design to maximize the efficiency in nonatomic congestion games. It is known that self-interested behavior among the players can damage the system's efficiency. Tax mechanisms is a common method to alleviate this issue and induce socially optimal behavior. In this work, we take the initial step for learning the optimal tax that can minimize the social cost with
-
Enhancing Multi-Criteria Decision Analysis with AI: Integrating Analytic Hierarchy Process and GPT-4 for Automated Decision Support arXiv.cs.MA Pub Date : 2024-02-12 Igor Svoboda, Dmytro Lande
Our study presents a new framework that incorporates the Analytic Hierarchy Process (AHP) and Generative Pre-trained Transformer 4 (GPT-4) large language model (LLM), bringing novel approaches to cybersecurity Multiple-criteria Decision Making (MCDA). By utilizing the capabilities of GPT-4 autonomous agents as virtual experts, we automate the decision-making process, enhancing both efficiency and reliability