Optimization and Learning in Open Multi-Agent Systems

2025-01-28 · Diego Deplano, Nicola Bastianello, Mauro Franceschelli, Karl H. Johansson

Modern artificial intelligence relies on networks of agents that collect data, process information, and exchange it with neighbors to collaboratively solve optimization and learning problems. This article introduces a novel distributed algorithm to address a broad class of these problems in "open networks", where the number of participating agents may vary due to several factors, such as autonomous decisions, heterogeneous resource availability, or DoS attacks. Extending the current literature, the convergence analysis of the proposed algorithm is based on the newly developed "Theory of Open Operators", which characterizes an operator as open when the set of components to be updated changes over time, yielding to time-varying operators acting on sequences of points of different dimensions and compositions. The mathematical tools and convergence results developed here provide a general framework for evaluating distributed algorithms in open networks, allowing to characterize their performance in terms of the punctual distance from the optimal solution, in contrast with regret-based metrics that assess cumulative performance over a finite-time horizon. As illustrative examples, the proposed algorithm is used to solve dynamic consensus or tracking problems on different metrics of interest, such as average, median, and min/max value, as well as classification problems with logistic loss functions.

📄 PDF Abstract BibTeX arXiv:2501.16847

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

AgenticTCAD: A LLM-based Multi-Agent Framework for Automated TCAD Code Generation and Device Optimization

2025-12-26 · Guangxi Fan, Tianliang Ma, Xuguang Sun, Xun Wang 외 arxiv

With the continued scaling of advanced technology nodes, the design-technology co-optimization (DTCO) paradigm has become increasingly critical, rendering efficient device design and optimization essential. In the domain…

Code Generation

MAS-PromptBench: When Does Prompt Optimization Improve Multi-Agent LLM Systems?

2026-06-22 · Juyang Bai, Laixi Shi arxiv

Multi-agent systems (MAS) offer a scalable path forward for agentic AI, comprising multiple LLM-based agents, each assigned a system prompt and a position within a workflow that governs inter-agent coordination and outpu…

PLATO: Pointer Learner for Agent and Task Openness

2026-07-27 · Alireza Saleh Abadi, Leen-Kiat Soh, Daniel Alan Redder, Adam Eck 외 arxiv

Open agent systems (OASYS) are increasingly prevalent in real-world domains where the sets of agents and tasks change unpredictably over time. Such openness, including agent openness (AO) and task openness (TO), poses a …

Multi-agent Reinforcement Learning Zero-shot Generalization Graph Neural Network

OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents

2026-06-01 · Rui Yang, Qianhui Wu, Yuxi Chen, Hao Bai 외 arxiv

Building capable visual web agents requires long-horizon reasoning, precise grounding, and robust interaction with dynamic real-world websites. Despite rapid progress, the strongest systems remain largely proprietary, wh…

Reinforcement Learning

PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems

2021-11-10 · David Biagioni, Xiangyu Zhang, Dylan Wald, Deepthi Vaidhynathan 외

We present the PowerGridworld software package to provide users with a lightweight, modular, and customizable framework for creating power-systems-focused, multi-agent Gym environments that readily integrate with existin…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)