English
Related papers

Related papers: Byzantine-Robust Decentralized Coordination of LLM…

200 papers

This paper proposes a Byzantine-resilient consensus framework that simultaneously pursues two tightly coupled objectives: actively identifying Byzantine agents and guaranteeing resilient consensus among normal agents. Unlike existing…

Optimization and Control · Mathematics 2026-05-13 Rui Huang , Changxin Liu , Wen-Hua Chen , Yang Shi

Federated learning (FL) enables multiple clients to collaboratively train machine learning models without revealing their private training data. In conventional FL, the system follows the server-assisted architecture (server-assisted FL),…

Cryptography and Security · Computer Science 2024-07-16 Minghong Fang , Zifan Zhang , Hairi , Prashant Khanduri , Jia Liu , Songtao Lu , Yuchen Liu , Neil Gong

We study a robust, i.e. in presence of malicious participants, multi-agent multi-armed bandit problem where multiple participants are distributed on a fully decentralized blockchain, with the possibility of some being malicious. The rewards…

Machine Learning · Computer Science 2024-07-29 Mengfan Xu , Diego Klabjan

The cooperative bandit problem is a multi-agent decision problem involving a group of agents that interact simultaneously with a multi-armed bandit, while communicating over a network with delays. The central idea in this problem is to…

Machine Learning · Statistics 2022-05-31 Abhimanyu Dubey , Alex Pentland

The problem of Byzantine consensus has been key to designing secure distributed systems. However, it is particularly difficult, mainly due to the presence of Byzantine processes that act arbitrarily and the unknown message delays in general…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-05-05 Alejandro Ranchal-Pedrosa , Vincent Gramoli

The Weighted-Mean Subsequence Reduced (W-MSR) algorithm, the state-of-the-art method for Byzantine-resilient design of decentralized multi-robot systems, is based on discarding outliers received over Linear Consensus Protocol (LCP).…

Robotics · Computer Science 2023-01-18 Kacper Wardega , Max von Hippel , Roberto Tron , Cristina Nita-Rotaru , Wenchao Li

Recent advances in generative AI have enabled sophisticated multi-agent architectures for healthcare, where large language models power collaborative clinical decision-making. However, these distributed systems face critical challenges in…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-23 Nihir Chadderwala

In this paper, we show synchronization for a group of output passive agents that communicate with each other according to an underlying communication graph to achieve a common goal. We propose a distributed event-triggered control framework…

Systems and Control · Computer Science 2017-10-02 Arash Rahnama , Panos J. Antsaklis

In this paper, we consider a resilient consensus problem for the multi-agent network where some of the agents are subject to Byzantine attacks and may transmit erroneous state values to their neighbors. In particular, we develop an…

Multiagent Systems · Computer Science 2023-06-07 Liwei Yuan , Hideaki Ishii

Decentralized stochastic gradient algorithms efficiently solve large-scale finite-sum optimization problems when all agents in the network are reliable. However, most of these algorithms are not resilient to adverse conditions, such as…

Optimization and Control · Mathematics 2025-06-24 Jinhui Hu , Guo Chen , Huaqing Li , Xiaoyu Guo , Liang Ran , Tingwen Huang

Most existing Large Language Model (LLM)-based agent frameworks rely on centralized orchestration, incurring high deployment costs, rigid communication topologies, and limited adaptability. To address these challenges, we introduce…

Machine Learning · Computer Science 2025-08-28 Ji Wang , Kashing Chen , Xinyuan Song , Ke Zhang , Lynn Ai , Eric Yang , Bill Shi

The rise of Agent AI and Large Language Model-powered Multi-Agent Systems (LLM-MAS) has underscored the need for responsible and dependable system operation. Tools like LangChain and Retrieval-Augmented Generation have expanded LLM…

Multiagent Systems · Computer Science 2025-02-05 Jinwei Hu , Yi Dong , Shuang Ao , Zhuoyun Li , Boxuan Wang , Lokesh Singh , Guangliang Cheng , Sarvapali D. Ramchurn , Xiaowei Huang

Multi-agent LLM systems improve reasoning by combining outputs from multiple agents, but interaction-heavy methods can introduce error propagation and high communication overhead. When agents exchange raw responses or reasoning traces,…

Artificial Intelligence · Computer Science 2026-05-26 Yi Li , Songtao Wei , Dongming Jiang , Zhichun Guo , Qiannan Li , Bingzhe Li

A flurry of recent work has demonstrated that pre-trained large language models (LLMs) can be effective task planners for a variety of single-robot tasks. The planning performance of LLMs is significantly improved via prompting techniques,…

Robotics · Computer Science 2024-03-25 Yongchao Chen , Jacob Arkin , Yang Zhang , Nicholas Roy , Chuchu Fan

Recently, decentralized learning has emerged as a popular peer-to-peer signal and information processing paradigm that enables model training across geographically distributed agents in a scalable manner, without the presence of any central…

Machine Learning · Computer Science 2024-07-12 Haoxiang Ye , Qing Ling

Many areas of deep learning benefit from using increasingly larger neural networks trained on public data, as is the case for pre-trained models for NLP and computer vision. Training such models requires a lot of computational resources…

Machine Learning · Computer Science 2023-01-03 Eduard Gorbunov , Alexander Borzunov , Michael Diskin , Max Ryabinin

In decentralized machine learning, different devices communicate in a peer-to-peer manner to collaboratively learn from each other's data. Such approaches are vulnerable to misbehaving (or Byzantine) devices. We introduce F-RG, a general…

Optimization and Control · Mathematics 2025-06-12 Renaud Gaucher , Aymeric Dieuleveut , Hadrien Hendrikx

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,…

Multiagent Systems · Computer Science 2024-07-11 Sumedh Rasal , E. J. Hauer

We consider the problem of Byzantine fault-tolerance in the peer-to-peer (P2P) distributed gradient-descent method -- a prominent algorithm for distributed optimization in a P2P system. In this problem, the system comprises of multiple…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-02-01 Nirupam Gupta , Nitin H. Vaidya

Large Language Models (LLMs) still face challenges when dealing with complex reasoning tasks, often resulting in hallucinations, which limit the practical application of LLMs. To alleviate this issue, this paper proposes a new method that…

Artificial Intelligence · Computer Science 2024-11-26 Zhihua Duan , Jialin Wang