Bregman Consensus

Andrei N. Soklakov

cs.MASep 28, 2026

Bregman Consensus

Authors: Andrei N. Soklakov

Abstract

Consider a community of agents who are seeking consensus on a set of parameters. The agents agree to use the same Bregman-type divergence to quantify disagreement between their individual estimates of the parameters but have varying confidence in each other's abilities. Each agent is happy to revise their estimate by moving to the weighted barycenter of all individual estimates with higher weights applied to more trusted agents. We show that such revisions naturally lead to an iterative algorithm which converges to a unique consensus estimate of the parameters. Furthermore, since the consensus estimate is itself a barycenter with computable weights, the group emerges as a collective super-agent with a well-formed opinion regarding the ability of each individual agent.

Explore similar work

The Cost of Consensus: Malignant Epistemic Herding and Adaptive Gating in Distributed Multi-Agent Search
May 7, 2026David Farr, Iain Cruickshank, Kate Starbird +1Multi-Agent Coordination Multi-Agent Planning
1*Information School, University of Washington, 1410 NE Campus Parkway, Seattle, 98195, WA, USA. · 2Computer Science, Carnegie Mellon University, 5000 Forbes Avenue,2026 Pittsburgh, 15213, PA, USA. · 3Human Centered Design Engineering, University of Washington, 1410 NE Campus Parkway, Seattle, 98195, WA, USA. +1
Beyond Consensus: Trace-Level Synthesis in Mixture of Agents
May 27, 2026Shreyas Fadnavis, Praitayini Kanakaraj, Felix WyssReasoning Traces Traces
Bioscope AI
Language-model groups overstate consensus when replaying human deliberation on a reasoning task
Sep 17, 2026Tengfei ShaoDeliberation Large Language Model Decisions
Global Education Center, Waseda University, Tokyo, Japan

May 7, 2026, cs.MAJ/K move · Enter open · S save

The Cost of Consensus: Malignant Epistemic Herding and Adaptive Gating in Distributed Multi-Agent Search

David Farr, Iain Cruickshank, Kate Starbird, Jevin West

1*Information School, University of Washington, 1410 NE Campus Parkway, Seattle, 98195, WA, USA. · 2Computer Science, Carnegie Mellon University, 5000 Forbes Avenue,2026 Pittsburgh, 15213, PA, USA. · 3Human Centered Design Engineering, University of Washington, 1410 NE Campus Parkway, Seattle, 98195, WA, USA.+1

Multi-Agent Coordination Multi-Agent Planning Epistemic Asymmetry Epistemic Integrity Kullback-Leibler Divergence

Open paper AskPDF arXiv

Distributed agents in real-world settings frequently must coordinate under uncertainty with only partial observations. Coordination is necessary to share beliefs to aid in task completion, but communication costs bandwidth, introduces latency, and if done poorly, can degrade collective reasoning. This tension is especially acute in bandwidth-constrained deployments such as distributed sensing networks, autonomous reconnaissance, and collaborative cyber defense, where excessive transmission carries direct operational costs. Existing work has focused on multi-agent exploration and communication strategies, but not on how communication frequency and content jointly shape the collective belief state. Central to this challenge is the degree to which agents maintain compatible internal beliefs about the environment, a property we term \textit{epistemic alignment}. When agents share beliefs effectively, they converge on correct hypotheses; when communication is poorly designed, agents may converge confidently on wrong ones. We formalize this distinction and show it is not detectable from coordination metrics alone such as Jensen-Shannon Divergence or rate to consensus.

Abstract

Explore similar work

The Cost of Consensus: Malignant Epistemic Herding and Adaptive Gating in Distributed Multi-Agent Search

Beyond Consensus: Trace-Level Synthesis in Mixture of Agents

Language-model groups overstate consensus when replaying human deliberation on a reasoning task