Tootfinder

Transforming Competition into Collaboration: The Revolutionary Role of Multi-Agent Systems and Language Models in Modern Organizations
Carlos Jose Xavier Cruz
https://arxiv.org/abs/2403.07769

Transforming Competition into Collaboration: The Revolutionary Role of Multi-Agent Systems and Language Models in Modern Organizations
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 to strategic decision making based on applied knowledge and human orchestration. Previous invest…

This https://arxiv.org/abs/2402.11550 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration
Large language models (LLMs) have demonstrated impressive performance in understanding language and executing complex reasoning tasks. However, LLMs with long context windows have been notorious for their expensive training costs and high inference latency. Even the most advanced models such as GPT-4 and Claude2 often make mistakes when processing inputs of over $100k$ tokens, a phenomenon also known as \textit{lost in the middle}. In this paper, we propose \textsc{LongAgent}, a method based on…

Transforming Competition into Collaboration: The Revolutionary Role of Multi-Agent Systems and Language Models in Modern Organizations
Carlos Jose Xavier Cruz
https://arxiv.org/abs/2403.07769

Transforming Competition into Collaboration: The Revolutionary Role of Multi-Agent Systems and Language Models in Modern Organizations
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 to strategic decision making based on applied knowledge and human orchestration. Previous invest…

Simulating Human Strategic Behavior: Comparing Single and Multi-agent LLMs
Karthik Sreedhar, Lydia Chilton
https://arxiv.org/abs/2402.08189 https://…

Simulating Human Strategic Behavior: Comparing Single and Multi-agent LLMs
When creating plans, policies, or applications for people, it is challenging for designers to think through the strategic ways that different people will behave. Recently, Large Language Models (LLMs) have been shown to create realistic simulations of human-like behavior based on personas. We build on this to investigate whether LLMs can simulate human strategic behavior. Human strategies are complex because they take into account social norms in addition to aiming to maximize personal gain. Th…

This https://arxiv.org/abs/2311.09618 has been replaced.
initial toot: https://mastoxiv.page/@arX…

Simulating Opinion Dynamics with Networks of LLM-based Agents
Accurately simulating human opinion dynamics is crucial for understanding a variety of societal phenomena, including polarization and the spread of misinformation. However, the agent-based models (ABMs) commonly used for such simulations often over-simplify human behavior. We propose a new approach to simulating opinion dynamics based on populations of Large Language Models (LLMs). Our findings reveal a strong inherent bias in LLM agents towards producing accurate information, leading simulated…

This https://arxiv.org/abs/2402.11550 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration
Large language models (LLMs) have demonstrated impressive performance in understanding language and executing complex reasoning tasks. However, LLMs with long context windows have been notorious for their expensive training costs and high inference latency. Even the most advanced models such as GPT-4 and Claude2 often make mistakes when processing inputs of over $100k$ tokens, a phenomenon also known as \textit{lost in the middle}. In this paper, we propose \textsc{LongAgent}, a method based on…

This https://arxiv.org/abs/2309.07055 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCY_…

Unraveling the Geography of Infection Spread: Harnessing Super-Agents for Predictive Modeling
Our study presents an intermediate-level modeling approach that bridges the gap between complex Agent-Based Models (ABMs) and traditional compartmental models for infectious diseases. We introduce "super-agents" to simulate infection spread in cities, reducing computational complexity while retaining individual-level interactions. This approach leverages real-world mobility data and strategic geospatial tessellations for efficiency. Voronoi Diagram tessellations, based on specific street networ…

This https://arxiv.org/abs/2403.03434 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csMA_…

An AI-enabled Agent-Based Model and Its Application in Measles Outbreak Simulation for New Zealand
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, enabling automated model calibration and reducing the computational resources needed for scaling up the model, we have developed a tensorized and differentiable agent-based model by coupling Graph Neural Network (GNN) and Long Short-Term Memory (LSTM) network. The …

LLM-Based Multi-Agent Systems for Software Engineering: Vision and the Road Ahead
Junda He, Christoph Treude, David Lo
https://arxiv.org/abs/2404.04834 htt…

LLM-Based Multi-Agent Systems for Software Engineering: Vision and the Road Ahead
Integrating Large Language Models(LLMs) into autonomous agents marks a significant shift in the research landscape by offering cognitive abilities competitive to human planning and reasoning. This paper envisions the evolution of LLM-based Multi-Agent (LMA) systems in addressing complex and multi-faceted software engineering challenges. LMA systems introduce numerous benefits, including enhanced robustness through collaborative cross-examination, autonomous problem-solving, and scalable solutio…

This https://arxiv.org/abs/2308.11959 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Scalable δ-Level Coherent State Synchronization of Multi-Agent Systems in the Presence of Bounded Disturbances
In this paper, we study scalable δ-Level coherent state synchronization for multi-agent systems (MAS) where the agents are subject to bounded disturbances/noises. We propose a scale-free framework designed solely based on the knowledge of agent models and agnostic to the communication graphs and size of the network. We define the level of coherency for each agent as the norm of the weighted sum of the disagreement dynamics with its neighbors. The objective is to restrict the level of coherency…

Variational Inference of Parameters in Opinion Dynamics Models
Jacopo Lenti, Fabrizio Silvestri, Gianmarco De Francisci Morales
https://arxiv.org/abs/2403.05358

Variational Inference of Parameters in Opinion Dynamics Models
Despite the frequent use of agent-based models (ABMs) for studying social phenomena, parameter estimation remains a challenge, often relying on costly simulation-based heuristics. This work uses variational inference to estimate the parameters of an opinion dynamics ABM, by transforming the estimation problem into an optimization task that can be solved directly. Our proposal relies on probabilistic generative ABMs (PGABMs): we start by synthesizing a probabilistic generative model from the A…

A Guide to Re-Implementing Agent-based Models: Experiences from the HUMAT Model
\"Onder G\"urcan, Timo Szczepanska, Patrycja Antosz
https://arxiv.org/abs/2405.03994

A Guide to Re-Implementing Agent-based Models: Experiences from the HUMAT Model
Replicating existing agent-based models poses significant challenges, particularly for those new to the field. This article presents an all-encompassing guide to re-implementing agent-based models, encompassing vital concepts such as comprehending the original model, utilizing agent-based modeling frameworks, simulation design, model validation, and more. By embracing the proposed guide, researchers and practitioners can gain a profound understanding of the entire re-implementation process, res…

A Model-based Multi-Agent Personalized Short-Video Recommender System
Peilun Zhou, Xiaoxiao Xu, Lantao Hu, Han Li, Peng Jiang
https://arxiv.org/abs/2405.01847

A Model-based Multi-Agent Personalized Short-Video Recommender System
Recommender selects and presents top-K items to the user at each online request, and a recommendation session consists of several sequential requests. Formulating a recommendation session as a Markov decision process and solving it by reinforcement learning (RL) framework has attracted increasing attention from both academic and industry communities. In this paper, we propose a RL-based industrial short-video recommender ranking framework, which models and maximizes user watch-time in an enviro…

Multi-Agent RL-Based Industrial AIGC Service Offloading over Wireless Edge Networks
Siyuan Li, Xi Lin, Hansong Xu, Kun Hua, Xiaomin Jin, Gaolei Li, Jianhua Li
https://arxiv.org/abs/2405.02972

Multi-Agent RL-Based Industrial AIGC Service Offloading over Wireless Edge Networks
Currently, the generative model has garnered considerable attention due to its application in addressing the challenge of scarcity of abnormal samples in the industrial Internet of Things (IoT). However, challenges persist regarding the edge deployment of generative models and the optimization of joint edge AI-generated content (AIGC) tasks. In this paper, we focus on the edge optimization of AIGC task execution and propose GMEL, a generative model-driven industrial AIGC collaborative edge lear…

A Guide to Re-Implementing Agent-based Models: Experiences from the HUMAT Model
\"Onder G\"urcan, Timo Szczepanska, Patrycja Antosz
https://arxiv.org/abs/2405.03994

A Guide to Re-Implementing Agent-based Models: Experiences from the HUMAT Model
Replicating existing agent-based models poses significant challenges, particularly for those new to the field. This article presents an all-encompassing guide to re-implementing agent-based models, encompassing vital concepts such as comprehending the original model, utilizing agent-based modeling frameworks, simulation design, model validation, and more. By embracing the proposed guide, researchers and practitioners can gain a profound understanding of the entire re-implementation process, res…

Partner selection and evolution of out-group avoidance
Hirofumi Takesue
https://arxiv.org/abs/2403.06893 https://arxiv.org/pdf/2403.0…

Partner selection and evolution of out-group avoidance
The preferential treatment of in-group members is widely observed. This study examines this phenomenon in the domain of cooperation in social dilemmas using evolutionary agent-based models that consider the role of partner selection. The model considers a repeated prisoner's dilemma game, in which agents belong to one of two groups that are distinguished by the continuation probability of pair interactions. On the basis of the behavior in the last round and the group affiliation of the partner,…

This https://arxiv.org/abs/2402.17785 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSD_…

ByteComposer: a Human-like Melody Composition Method based on Language Model Agent
Large Language Models (LLM) have shown encouraging progress in multimodal understanding and generation tasks. However, how to design a human-aligned and interpretable melody composition system is still under-explored. To solve this problem, we propose ByteComposer, an agent framework emulating a human's creative pipeline in four separate steps : "Conception Analysis - Draft Composition - Self-Evaluation and Modification - Aesthetic Selection". This framework seamlessly blends the interactive an…

This https://arxiv.org/abs/2404.10861 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csNE_…

Trackable Agent-based Evolution Models at Wafer Scale
Continuing improvements in computing hardware are poised to transform capabilities for in silico modeling of cross-scale phenomena underlying major open questions in evolutionary biology and artificial life, such as transitions in individuality, eco-evolutionary dynamics, and rare evolutionary events. Emerging ML/AI-oriented hardware accelerators, like the 850,000 processor Cerebras Wafer Scale Engine (WSE), hold particular promise. However, practical challenges remain in conducting informative…

This https://arxiv.org/abs/2404.18704 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

A geometric approach for stability analysis of delay systems: Applications to network dynamics
Investigating the network stability or synchronization dynamics of multi-agent systems with time delays is of significant importance in numerous real-world applications. Such investigations often rely on solving the transcendental characteristic equations (TCEs) obtained from linearization of the considered systems around specific solutions. While stability results based on the TCEs with real-valued coefficients induced by symmetric networks in time-delayed models have been extensively explored…

The importance of the incubation time distribution in compartmental epidemiological models
Eric Rozan, Marcelo N Kuperman, Sebastian Bouzat
https://arxiv.org/abs/2403.04505

The importance of the incubation time distribution in compartmental epidemiological models
This study investigates the utilization of various mathematical models for comprehending and managing outbreaks of infectious diseases, with a specific focus on how different distributions of incubation times influence predictions regarding epidemics. Two methodologies are examined: a compartmental SEnIR ODE model, which represents an enhanced version of the mean-field SEIR model, and a stochastic agent-based complex network model. Our findings demonstrate that the selection of diverse incubati…

Dynamic Human Trust Modeling of Autonomous Agents With Varying Capability and Strategy
Jason Dekarske (University of California, Davis), Zhaodan Kong (University of California, Davis), Sanjay Joshi (University of California, Davis)
https://arxiv.org/abs/2404.19291 https://arxiv.org/pdf/2404.19291
arXiv:2404.19291v1 Announce Type: new
Abstract: Objective We model the dynamic trust of human subjects in a human-autonomy-teaming screen-based task.
Background Trust is an emerging area of study in human-robot collaboration. Many studies have looked at the issue of robot performance as a sole predictor of human trust, but this could underestimate the complexity of the interaction.
Method Subjects were paired with autonomous agents to search an on-screen grid to determine the number of outlier objects. In each trial, a different autonomous agent with a preassigned capability used one of three search strategies and then reported the number of outliers it found as a fraction of its capability. Then, the subject reported their total outlier estimate. Human subjects then evaluated statements about the agent's behavior, reliability, and their trust in the agent.
Results 80 subjects were recruited. Self-reported trust was modeled using Ordinary Least Squares, but the group that interacted with varying capability agents on a short time order produced a better performing ARIMAX model. Models were cross-validated between groups and found a moderate improvement in the next trial trust prediction.
Conclusion A time series modeling approach reveals the effects of temporal ordering of agent performance on estimated trust. Recency bias may affect how subjects weigh the contribution of strategy or capability to trust. Understanding the connections between agent behavior, agent performance, and human trust is crucial to improving human-robot collaborative tasks.
Application The modeling approach in this study demonstrates the need to represent autonomous agent characteristics over time to capture changes in human trust.

Control of high-dimensional collective dynamics by deep neural feedback laws and kinetic modelling
Giacomo Albi, Sara Bicego, Dante Kalise
https://arxiv.org/abs/2404.02825

Control of high-dimensional collective dynamics by deep neural feedback laws and kinetic modelling
Modeling and control of agent-based models is twice cursed by the dimensionality of the problem, as both the number of agents and their state space dimension can be large. Even though the computational barrier posed by a large ensemble of agents can be overcome through a mean field formulation of the control problem, the feasibility of its solution is generally guaranteed only for agents operating in low-dimensional spaces. To circumvent the difficulty posed by the high dimensionality of the st…

CACTUS: Chemistry Agent Connecting Tool-Usage to Science
Andrew D. McNaughton, Gautham Ramalaxmi, Agustin Kruel, Carter R. Knutson, Rohith A. Varikoti, Neeraj Kumar
https://arxiv.org/abs/2405.00972

CACTUS: Chemistry Agent Connecting Tool-Usage to Science
Large language models (LLMs) have shown remarkable potential in various domains, but they often lack the ability to access and reason over domain-specific knowledge and tools. In this paper, we introduced CACTUS (Chemistry Agent Connecting Tool-Usage to Science), an LLM-based agent that integrates cheminformatics tools to enable advanced reasoning and problem-solving in chemistry and molecular discovery. We evaluate the performance of CACTUS using a diverse set of open-source LLMs, including Ge…

A Unified Debugging Approach via LLM-Based Multi-Agent Synergy
Cheryl Lee, Chunqiu Steven Xia, Jen-tse Huang, Zhouruixin Zhu, Lingming Zhang, Michael R. Lyu
https://arxiv.org/abs/2404.17153

A Unified Debugging Approach via LLM-Based Multi-Agent Synergy
Tremendous efforts have been devoted to automating software debugging, a time-consuming process involving fault localization and repair generation. Recently, Large Language Models (LLMs) have shown great potential in automated debugging. However, we identified three challenges posed to traditional and LLM-based debugging tools: 1) the upstream imperfection of fault localization affects the downstream repair, 2) the deficiency in handling complex logic errors, and 3) the ignorance of program con…

A Pontryagin Maximum Principle for agent-based models with convex state space
Stefano Almi, Riccardo Durastanti, Francesco Solombrino
https://arxiv.org/abs/2402.13680

A Pontryagin Maximum Principle for agent-based models with convex state space
We derive a first order optimality condition for a class of agent-based systems, as well as for their mean-field counterpart. A relevant difficulty of our analysis is that the state equation is formulated on possibly infinite-dimensional convex subsets of Banach spaces, as required by some problems in multi-population dynamics. Due to the lack of a linear structure and of local compactness, the usual tools of needle variations and linearisation procedures used to derive Pontryagin type conditio…

Go Beyond Black-box Policies: Rethinking the Design of Learning Agent for Interpretable and Verifiable HVAC Control
Zhiyu An, Xianzhong Ding, Wan Du
https://arxiv.org/abs/2403.00172

Go Beyond Black-box Policies: Rethinking the Design of Learning Agent for Interpretable and Verifiable HVAC Control
Recent research has shown the potential of Model-based Reinforcement Learning (MBRL) to enhance energy efficiency of Heating, Ventilation, and Air Conditioning (HVAC) systems. However, existing methods rely on black-box thermal dynamics models and stochastic optimizers, lacking reliability guarantees and posing risks to occupant health. In this work, we overcome the reliability bottleneck by redesigning HVAC controllers using decision trees extracted from existing thermal dynamics models and hi…

Analysis of Phylogeny Tracking Algorithms for Serial and Multiprocess Applications
Matthew Andres Moreno, Santiago Rodriguez Papa, Emily Dolson
https://arxiv.org/abs/2403.00246

Analysis of Phylogeny Tracking Algorithms for Serial and Multiprocess Applications
Since the advent of modern bioinformatics, the challenging, multifaceted problem of reconstructing phylogenetic history from biological sequences has hatched perennial statistical and algorithmic innovation. Studies of the phylogenetic dynamics of digital, agent-based evolutionary models motivate a peculiar converse question: how to best engineer tracking to facilitate fast, accurate, and memory-efficient lineage reconstructions? Here, we formally describe procedures for phylogenetic analysis i…

An AI-enabled Agent-Based Model and Its Application in Measles Outbreak Simulation for New Zealand
Sijin Zhang, Alvaro Orsi, Richard Dean, Lei Chen, Rachel Qiu, Jiawei Zhao
https://arxiv.org/abs/2403.03434

An AI-enabled Agent-Based Model and Its Application in Measles Outbreak Simulation for New Zealand
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, enabling automated model calibration and reducing the computational resources needed for scaling up the model, we have developed a tensorized and differentiable agent-based model by coupling Graph Neural Network (GNN) and Long Short-Term Memory (LSTM) network. The …

This https://arxiv.org/abs/2312.15910 has been replaced.
link: https://scholar.google.com/scholar?q=a

Reinforcement Unlearning
Machine unlearning refers to the process of mitigating the influence of specific training data on machine learning models based on removal requests from data owners. However, one important area that has been largely overlooked in the research of unlearning is reinforcement learning. Reinforcement learning focuses on training an agent to make optimal decisions within an environment to maximize its cumulative rewards. During the training, the agent tends to memorize the features of the environmen…

A Belief Propagation Algorithm for Multipath-based SLAM with Multiple Map Features: A mmWave MIMO Application
Xuhong Li, Xuesong Cai, Erik Leitinger, Fredrik Tufvesson
https://arxiv.org/abs/2403.10095

A Belief Propagation Algorithm for Multipath-based SLAM with Multiple Map Features: A mmWave MIMO Application
In this paper, we present a multipath-based simultaneous localization and mapping (SLAM) algorithm that continuously adapts mulitiple map feature (MF) models describing specularly reflected multipath components (MPCs) from flat surfaces and point-scattered MPCs, respectively. We develop a Bayesian model for sequential detection and estimation of interacting MF model parameters, MF states and mobile agent's state including position and orientation. The Bayesian model is represented by a factor g…

ByteComposer: a Human-like Melody Composition Method based on Language Model Agent
Xia Liang, Jiaju Lin, Xinjian Du
https://arxiv.org/abs/2402.17785 https:…

ByteComposer: a Human-like Melody Composition Method based on Language Model Agent
Large Language Models (LLM) have shown encouraging progress in multimodal understanding and generation tasks. However, how to design a human-aligned and interpretable melody composition system is still under-explored. To solve this problem, we propose ByteComposer, an agent framework emulating a human's creative pipeline in four separate steps : "Conception Analysis - Draft Composition - Self-Evaluation and Modification - Aesthetic Selection". This framework seamlessly blends the interactive an…

Modelling crypto markets by multi-agent reinforcement learning
Johann Lussange, Stefano Vrizzi, Stefano Palminteri, Boris Gutkin
https://arxiv.org/abs/2402.10803

Modelling crypto markets by multi-agent reinforcement learning
Building on a previous foundation work (Lussange et al. 2020), this study introduces a multi-agent reinforcement learning (MARL) model simulating crypto markets, which is calibrated to the Binance's daily closing prices of $153$ cryptocurrencies that were continuously traded between 2018 and 2022. Unlike previous agent-based models (ABM) or multi-agent systems (MAS) which relied on zero-intelligence agents or single autonomous agent methodologies, our approach relies on endowing agents with rei…

This https://arxiv.org/abs/2312.09007 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIT_…

LLMind: Orchestrating AI and IoT with LLM for Complex Task Execution
The exploration of large language models (LLMs) for task planning and IoT automation has recently gained significant attention. However, existing works suffer from limitations in terms of resource accessibility, complex task planning, and efficiency. In this paper, we present LLMind, an LLM-based AI agent framework that enables effective collaboration among IoT devices for executing complex tasks. Inspired by the functional specialization theory of the brain, our framework integrates an LLM wit…

MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution
Wei Tao, Yucheng Zhou, Wenqiang Zhang, Yu Cheng
https://arxiv.org/abs/2403.17927 https:/…

MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution
In software evolution, resolving the emergent issues within GitHub repositories is a complex challenge that involves not only the incorporation of new code but also the maintenance of existing functionalities. Large Language Models (LLMs) have shown promise in code generation and understanding but face difficulties in code change, particularly at the repository level. To overcome these challenges, we empirically study the reason why LLMs mostly fail to resolve GitHub issues and analyze some imp…

Trackable Agent-based Evolution Models at Wafer Scale
Matthew Andres Moreno, Connor Yang, Emily Dolson, Luis Zaman
https://arxiv.org/abs/2404.10861 https:/…

Trackable Agent-based Evolution Models at Wafer Scale
Continuing improvements in computing hardware are poised to transform capabilities for in silico modeling of cross-scale phenomena underlying major open questions in evolutionary biology and artificial life, such as transitions in individuality, eco-evolutionary dynamics, and rare evolutionary events. Emerging ML/AI-oriented hardware accelerators, like the 850,000 processor Cerebras Wafer Scale Engine (WSE), hold particular promise. However, practical challenges remain in conducting informative…

VCounselor: A Psychological Intervention Chat Agent Based on a Knowledge-Enhanced Large Language Model
H. Zhang, Z. Qiao, H. Wang, B. Duan, J. Yin
https://arxiv.org/abs/2403.13553

VCounselor: A Psychological Intervention Chat Agent Based on a Knowledge-Enhanced Large Language Model
Conversational artificial intelligence can already independently engage in brief conversations with clients with psychological problems and provide evidence-based psychological interventions. The main objective of this study is to improve the effectiveness and credibility of the large language model in psychological intervention by creating a specialized agent, the VCounselor, to address the limitations observed in popular large language models such as ChatGPT in domain applications. We achieve…

Rank-Dependent Predictable Forward Performance Processes
Bahman Angoshtari, Shida Duan
https://arxiv.org/abs/2403.16228 https://arxiv…

Rank-Dependent Predictable Forward Performance Processes
Predictable forward performance processes (PFPPs) are stochastic optimal control frameworks for an agent who controls a randomly evolving system but can only prescribe the system dynamics for a short period ahead. This is a common scenario in which a controlling agent frequently re-calibrates her model. We introduce a new class of PFPPs based on rank-dependent utility, generalizing existing models that are based on expected utility theory (EUT). We establish existence of rank-dependent PFPPs un…

This https://arxiv.org/abs/2402.01680 has been replaced.
link: https://scholar.google.com/scholar?q=a

Large Language Model based Multi-Agents: A Survey of Progress and Challenges
Large Language Models (LLMs) have achieved remarkable success across a wide array of tasks. Due to the impressive planning and reasoning abilities of LLMs, they have been used as autonomous agents to do many tasks automatically. Recently, based on the development of using one LLM as a single planning or decision-making agent, LLM-based multi-agent systems have achieved considerable progress in complex problem-solving and world simulation. To provide the community with an overview of this dynami…

A geometric approach for stability analysis of delay systems: Applications to network dynamics
Shijie Zhou, Wei Lin
https://arxiv.org/abs/2404.18704 https:…

A geometric approach for stability analysis of delay systems: Applications to network dynamics
Investigating the network stability or synchronization dynamics of multi-agent systems with time delays is of significant importance in numerous real-world applications. Such investigations often rely on solving the transcendental characteristic equations (TCEs) obtained from linearization of the considered systems around specific solutions. While stability results based on the TCEs with real-valued coefficients induced by symmetric networks in time-delayed models have been extensively explored…

Modeling the Spread of COVID-19 in University Communities
Jeffrey W. Herrmann, Hongjie Liu, Donald K. Milton
https://arxiv.org/abs/2403.10402 https://

Modeling the Spread of COVID-19 in University Communities
Mathematical and simulation models are often used to predict the spread of a disease and estimate the impact of public health interventions, and many such models have been developed and used during the COVID-19 pandemic. This paper describes a study that systematically compared models for a university community, which has a much smaller but more connected population than a state or nation. We developed a stochastic agent-based model, a deterministic compartment model, and a model based on ordin…

NeSy is alive and well: A LLM-driven symbolic approach for better code comment data generation and classification
Hanna Abi Akl
https://arxiv.org/abs/2402.16910

NeSy is alive and well: A LLM-driven symbolic approach for better code comment data generation and classification
We present a neuro-symbolic (NeSy) workflow combining a symbolic-based learning technique with a large language model (LLM) agent to generate synthetic data for code comment classification in the C programming language. We also show how generating controlled synthetic data using this workflow fixes some of the notable weaknesses of LLM-based generation and increases the performance of classical machine learning models on the code comment classification task. Our best model, a Neural Network, ac…

L3GO: Language Agents with Chain-of-3D-Thoughts for Generating Unconventional Objects
Yutaro Yamada, Khyathi Chandu, Yuchen Lin, Jack Hessel, Ilker Yildirim, Yejin Choi
https://arxiv.org/abs/2402.09052

L3GO: Language Agents with Chain-of-3D-Thoughts for Generating Unconventional Objects
Diffusion-based image generation models such as DALL-E 3 and Stable Diffusion-XL demonstrate remarkable capabilities in generating images with realistic and unique compositions. Yet, these models are not robust in precisely reasoning about physical and spatial configurations of objects, especially when instructed with unconventional, thereby out-of-distribution descriptions, such as "a chair with five legs". In this paper, we propose a language agent with chain-of-3D-thoughts (L3GO), an inferen…

This https://arxiv.org/abs/2310.06155 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csHC_…

CoQuest: Exploring Research Question Co-Creation with an LLM-based Agent
Developing novel research questions (RQs) often requires extensive literature reviews, especially in interdisciplinary fields. To support RQ development through human-AI co-creation, we leveraged Large Language Models (LLMs) to build an LLM-based agent system named CoQuest. We conducted an experiment with 20 HCI researchers to examine the impact of two interaction designs: breadth-first and depth-first RQ generation. The findings revealed that participants perceived the breadth-first approach a…

Navigating simplicity and complexity of social-ecological systems through a dialog between dynamical systems and agent-based models
Sonja Radosavljevic, Udita Sanga, Maja Schl\"uter
https://arxiv.org/abs/2402.12086

Navigating simplicity and complexity of social-ecological systems through a dialog between dynamical systems and agent-based models
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 models (DSM) or agent-based models (ABM). Both modeling approaches have strengths and weakn…

L3GO: Language Agents with Chain-of-3D-Thoughts for Generating Unconventional Objects
Yutaro Yamada, Khyathi Chandu, Yuchen Lin, Jack Hessel, Ilker Yildirim, Yejin Choi
https://arxiv.org/abs/2402.09052

L3GO: Language Agents with Chain-of-3D-Thoughts for Generating Unconventional Objects
Diffusion-based image generation models such as DALL-E 3 and Stable Diffusion-XL demonstrate remarkable capabilities in generating images with realistic and unique compositions. Yet, these models are not robust in precisely reasoning about physical and spatial configurations of objects, especially when instructed with unconventional, thereby out-of-distribution descriptions, such as "a chair with five legs". In this paper, we propose a language agent with chain-of-3D-thoughts (L3GO), an inferen…

This https://arxiv.org/abs/2404.11459 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Octopus v3: Technical Report for On-device Sub-billion Multimodal AI Agent
A multimodal AI agent is characterized by its ability to process and learn from various types of data, including natural language, visual, and audio inputs, to inform its actions. Despite advancements in large language models that incorporate visual data, such as GPT-4V, effectively translating image-based data into actionable outcomes for AI agents continues to be challenging. In this paper, we introduce a multimodal model that incorporates the concept of functional token specifically designed…

SONATA: Self-adaptive Evolutionary Framework for Hardware-aware Neural Architecture Search
Halima Bouzidi, Smail Niar, Hamza Ouarnoughi, El-Ghazali Talbi
https://arxiv.org/abs/2402.13204 https://arxiv.org/pdf/2402.13204
arXiv:2402.13204v1 Announce Type: new
Abstract: Recent advancements in Artificial Intelligence (AI), driven by Neural Networks (NN), demand innovative neural architecture designs, particularly within the constrained environments of Internet of Things (IoT) systems, to balance performance and efficiency. HW-aware Neural Architecture Search (HW-aware NAS) emerges as an attractive strategy to automate the design of NN using multi-objective optimization approaches, such as evolutionary algorithms. However, the intricate relationship between NN design parameters and HW-aware NAS optimization objectives remains an underexplored research area, overlooking opportunities to effectively leverage this knowledge to guide the search process accordingly. Furthermore, the large amount of evaluation data produced during the search holds untapped potential for refining the optimization strategy and improving the approximation of the Pareto front. Addressing these issues, we propose SONATA, a self-adaptive evolutionary algorithm for HW-aware NAS. Our method leverages adaptive evolutionary operators guided by the learned importance of NN design parameters. Specifically, through tree-based surrogate models and a Reinforcement Learning agent, we aspire to gather knowledge on 'How' and 'When' to evolve NN architectures. Comprehensive evaluations across various NAS search spaces and hardware devices on the ImageNet-1k dataset have shown the merit of SONATA with up to 0.25% improvement in accuracy and up to 2.42x gains in latency and energy. Our SONATA has seen up to sim$93.6% Pareto dominance over the native NSGA-II, further stipulating the importance of self-adaptive evolution operators in HW-aware NAS.

Language Evolution with Deep Learning
Mathieu Rita, Paul Michel, Rahma Chaabouni, Olivier Pietquin, Emmanuel Dupoux, Florian Strub
https://arxiv.org/abs/2403.11958

Language Evolution with Deep Learning
Computational modeling plays an essential role in the study of language emergence. It aims to simulate the conditions and learning processes that could trigger the emergence of a structured language within a simulated controlled environment. Several methods have been used to investigate the origin of our language, including agent-based systems, Bayesian agents, genetic algorithms, and rule-based systems. This chapter explores another class of computational models that have recently revolutioniz…

SONATA: Self-adaptive Evolutionary Framework for Hardware-aware Neural Architecture Search
Halima Bouzidi, Smail Niar, Hamza Ouarnoughi, El-Ghazali Talbi
https://arxiv.org/abs/2402.13204 https://arxiv.org/pdf/2402.13204
arXiv:2402.13204v1 Announce Type: new
Abstract: Recent advancements in Artificial Intelligence (AI), driven by Neural Networks (NN), demand innovative neural architecture designs, particularly within the constrained environments of Internet of Things (IoT) systems, to balance performance and efficiency. HW-aware Neural Architecture Search (HW-aware NAS) emerges as an attractive strategy to automate the design of NN using multi-objective optimization approaches, such as evolutionary algorithms. However, the intricate relationship between NN design parameters and HW-aware NAS optimization objectives remains an underexplored research area, overlooking opportunities to effectively leverage this knowledge to guide the search process accordingly. Furthermore, the large amount of evaluation data produced during the search holds untapped potential for refining the optimization strategy and improving the approximation of the Pareto front. Addressing these issues, we propose SONATA, a self-adaptive evolutionary algorithm for HW-aware NAS. Our method leverages adaptive evolutionary operators guided by the learned importance of NN design parameters. Specifically, through tree-based surrogate models and a Reinforcement Learning agent, we aspire to gather knowledge on 'How' and 'When' to evolve NN architectures. Comprehensive evaluations across various NAS search spaces and hardware devices on the ImageNet-1k dataset have shown the merit of SONATA with up to 0.25% improvement in accuracy and up to 2.42x gains in latency and energy. Our SONATA has seen up to sim$93.6% Pareto dominance over the native NSGA-II, further stipulating the importance of self-adaptive evolution operators in HW-aware NAS.

An Agent-Based Model of Elephant Crop Raid Dynamics in the Periyar-Agasthyamalai Complex, India
Purathekandy Anjali, Meera Anna Oommen, Martin Wikelski, Deepak N Subramani
https://arxiv.org/abs/2404.09024

An Agent-Based Model of Elephant Crop Raid Dynamics in the Periyar-Agasthyamalai Complex, India
Human-wildlife conflict poses significant challenges to conservation efforts around the world and requires innovative solutions for effective management. We developed an agent-based model to simulate complex interactions between humans and Asian elephants (particularly solitary bull elephants) in the Periyar-Agasthyamalai complex of the Western Ghats in Kerala, India. Incorporating factors such as crop habituation, thermoregulation needs, and aggression models, this framework enables the evalua…

Liquid-Graph Time-Constant Network for Multi-Agent Systems Control
Antonio Marino (UR, CNRS), Claudio Pacchierotti (RAINBOW), Paolo Robuffo Giordano (RAINBOW)
https://arxiv.org/abs/2404.13982

Liquid-Graph Time-Constant Network for Multi-Agent Systems Control
In this paper, we propose the Liquid-Graph Time-constant (LGTC) network, a continuous graph neural network(GNN) model for control of multi-agent systems based on therecent Liquid Time Constant (LTC) network. We analyse itsstability leveraging contraction analysis and propose a closed-form model that preserves the model contraction rate and doesnot require solving an ODE at each iteration. Compared todiscrete models like Graph Gated Neural Networks (GGNNs),the higher expressivity of the proposed…

This https://arxiv.org/abs/2402.11453 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization
Scientific data visualization plays a crucial role in research by enabling the direct display of complex information and assisting researchers in identifying implicit patterns. Despite its importance, the use of Large Language Models (LLMs) for scientific data visualization remains rather unexplored. In this study, we introduce MatPlotAgent, an efficient model-agnostic LLM agent framework designed to automate scientific data visualization tasks. Leveraging the capabilities of both code LLMs and…

A biologically inspired computational trust model for open multi-agent systems which is resilient to trustor population changes
Zoi Lygizou, Dimitris Kalles
https://arxiv.org/abs/2404.10014

A biologically inspired computational trust model for open multi-agent systems which is resilient to trustor population changes
Current trust and reputation models continue to have significant limitations, such as the inability to deal with agents constantly entering or exiting open multi-agent systems (open MAS), as well as continuously changing behaviors. Our study is based on CA, a previously proposed decentralized computational trust model from the trustee's point of view, inspired by synaptic plasticity and the formation of assemblies in the human brain. It is designed to meet the requirements of highly dynamic and…