Dynamic Trust-Aware Sparse Communication Topology for LLM-Based Multi-Agent Consensus

2026-06-01 · Wanshuang Gou, Zihan Liu arxiv

Large language model-driven multi-agent systems enhance the reliability of complex reasoning tasks through multi-round deliberation, role specialization, and cross-validation. However, existing multi-agent debate and collaboration frameworks typically adopt fully connected communication, causing the number of messages, token costs, and end-to-end latency to grow approximately quadratically with the number of agents; although fixed sparse topologies reduce overhead, they cannot adapt communication relationships to different task instances or intermediate reasoning states, making them prone either to preserving low-value interactions or to losing critical error-correction information. To address this problem, this paper proposes DySCo (Dynamic Sparse Consensus), a dynamic trust-aware sparse consensus mechanism. In each round of reasoning, DySCo estimates the value of communication edges based on agent reliability, answer divergence, and task relevance, and selects a small number of high-value edges for message exchange under budget constraints; it then aggregates the answers of different agents through dynamic trust weights and terminates the discussion early once consensus stabilizes. This mechanism replaces universal broadcasting with on-demand communication, thereby reducing communication overhead while preserving essential cross-validation information. We further present analyses of communication complexity and consensus stability, and evaluate the performance of DySCo on mathematical reasoning, logical reasoning, and factual question-answering tasks.

📄 PDF Abstract BibTeX arXiv:2606.01828

Code (0)

등록된 구현이 없습니다.

Tasks

Mathematical Reasoning Logical Reasoning

FedRings: A Scalable and Topology-Aware Federated Learning Framework for LEO Satellite Constellations

2026-08-04 · Ziwu Liu, Inês Pinto Gouveia, Rehana Yasmin, Paulo Esteves-Verissimo 외 arxiv

Federated learning over low Earth orbit (LEO) satellite networks is limited by frequent link changes, short contact times, and a highly dynamic topology, making centralized or synchronized training inefficient and hard t…

Federated Learning

TA-MoE: Topology-Aware Large Scale Mixture-of-Expert Training

2023-02-20 · Chang Chen, Min Li, Zhihua Wu, dianhai yu 외

Sparsely gated Mixture-of-Expert (MoE) has demonstrated its effectiveness in scaling up deep neural networks to an extreme scale. Despite that numerous efforts have been made to improve the performance of MoE from the mo…

Topology-Aware Revival for Efficient Sparse Training

2026-02-04 · Meiling Jin, Fei Wang, Xiaoyun Yuan, Chen Qian 외 arxiv

Static sparse training is a promising route to efficient learning by committing to a fixed mask pattern, yet the constrained structure reduces robustness. Early pruning decisions can lock the network into a brittle struc…

Reinforcement Learning

AI-Native Integrated Sensing and Communications for Self-Organizing Wireless Networks: Architectures, Learning Paradigms, and System-Level Design

2025-12-29 · S. Zhang, M. Feizarefi, A. F. Mirzaei arxiv

Integrated Sensing and Communications (ISAC) is emerging as a foundational paradigm for next-generation wireless networks, enabling communication infrastructures to simultaneously support data transmission and environmen…

Reinforcement Learning

TAS-GNN: A Status-Aware Signed Graph Neural Network for Anomaly Detection in Bitcoin Trust Systems

2026-02-28 · Chang Xue, Fang Liu, Jiaye Wang, Jinming Xing 외 arxiv

Decentralized financial platforms rely heavily on Web of Trust reputation systems to mitigate counterparty risk in the absence of centralized identity verification. However, these pseudonymous networks are inherently vul…

Graph Neural Network Anomaly Detection