Related papers: Byzantine-Robust Decentralized Coordination of LLM…
We address the challenges of Byzantine-robust training in asynchronous distributed machine learning systems, aiming to enhance efficiency amid massive parallelization and heterogeneous computing resources. Asynchronous systems, marked by…
This paper studies the distributed multi-agent resilient optimization problem under the f-total Byzantine attacks. Compared with the previous work on Byzantineresilient multi-agent exact optimization problems, we do not require the…
Large language models (LLMs) and LLM-based agents are increasingly deployed as assistants in planning and decision making, yet most existing systems are implicitly optimized for a single-principal interaction paradigm, in which the model is…
We consider a distributed reinforcement learning setting where multiple agents separately explore the environment and communicate their experiences through a central server. However, $\alpha$-fraction of agents are adversarial and can…
This report considers the problem of Byzantine fault-tolerance in synchronous parallelized learning that is founded on the parallelized stochastic gradient descent (parallelized-SGD) algorithm. The system comprises a master, and $n$…
Multi-agent LLM frameworks are widely used to accelerate the development of agent systems powered by large language models (LLMs). These frameworks impose distinct architectural structures that govern how agents interact, store information,…
In this paper, we present an efficient deterministic algorithm for consensus in presence of Byzantine failures. Our algorithm achieves consensus on an $L$-bit value with communication complexity $O(nL + n^4 L^{0.5} + n^6)$ bits, in a…
Large Language Models (LLMs) have demonstrated advanced capabilities but often suffer from factual inaccuracies (hallucinations) and systematic biases. These issues, sometimes amplified in specific architectures like Mixture-of-Experts…
In this study, we explore the robustness of cooperative multi-agent reinforcement learning (c-MARL) against Byzantine failures, where any agent can enact arbitrary, worst-case actions due to malfunction or adversarial attack. To address the…
We consider the federated learning problem where data on workers are not independent and identically distributed (i.i.d.). During the learning process, an unknown number of Byzantine workers may send malicious messages to the central node,…
Most of the Blockchain permissioned systems employ Byzantine fault-tolerance (BFT) consensus protocols to ensure that honest validators agree on the order for appending entries to their ledgers. In this paper, we study the performance and…
Large language models (LLMs) have revolutionized medical reasoning tasks, yet single-agent systems often falter on complex, interdisciplinary problems requiring robust handling of uncertainty and conflicting evidence. Multi-agent systems…
Online coordination of multi-robot systems in open and unknown environments faces significant challenges, particularly when semantic features detected during operation dynamically trigger new tasks. Recent large language model (LLMs)-based…
Remarkable performance of large language models (LLMs) in a variety of tasks brings forth many opportunities as well as challenges of utilizing them in production settings. Towards practical adoption of LLMs, multi-agent systems hold great…
Although large language model (LLM) based multi-agent systems (MAS) show their capability to solve complex tasks and achieve higher performance over single agent systems, they lead to huge computational overheads because of heavy…
The safety-critical scenarios of artificial intelligence (AI), such as autonomous driving, Internet of Things, smart healthcare, etc., have raised critical requirements of trustworthy AI to guarantee the privacy and security with reliable…
This paper considers a distributed optimization problem in the presence of Byzantine agents capable of introducing untrustworthy information into the communication network. A resilient distributed subgradient algorithm is proposed based on…
In this paper, we study the challenging task of Byzantine-robust decentralized training on arbitrary communication graphs. Unlike federated learning where workers communicate through a server, workers in the decentralized environment can…
The widespread adoption of large-scale machine learning models in recent years highlights the need for distributed computing for efficiency and scalability. This work introduces a novel distributed machine learning paradigm --…
As agentic AI becomes more widespread, agents with distinct and possibly conflicting goals will interact in complex ways. These multi-agent interactions pose a fundamental challenge, particularly in social dilemmas, where agents' individual…