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

• URL: http://arxiv.org/abs/2605.06988v1
• Date: Thu, 07 May 2026 22:07:25 GMT
• Title: The Cost of Consensus: Malignant Epistemic Herding and Adaptive Gating in Distributed Multi-Agent Search
• Abstract summary: 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.<n>This tension is especially acute in bandwidth-constrained deployments such as distributed sensing networks, autonomous reconnaissance, and collaborative cyber defense.<n>We formalize this distinction and show it is not detectable from coordination metrics alone such as Jensen-Shannon Divergence or rate to consensus.
• Score: 2.435326482104274
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Anytime Plug-and-Play Control with Contract-Based Distributed MPC [3.477704547618128]
  This work introduces a distributed multi-agent control algorithm based on local communication that supports anytime agent joining and leaving the communication network without centralized coordination.<n>We validate the proposed method in an autonomous multi-agent driving scenario, demonstrating effective collision avoidance in high-speed, dynamic environments with agents moving in opposite directions.
  arXiv  Detail & Related papers  (2026-07-05T10:06:49Z)
• Talk is Cheap, Communication is Hard: Dynamic Grounding Failures and Repair in Multi-Agent Negotiation [2.5089149965583086]
  Grounding is the collaborative process of establishing mutual belief sufficient for the current communicative purpose.<n>Current multi-agent Large Language Model (LLM) benchmarks focus on static, one-shot tasks.<n>We introduce an iterated, multi-turn negotiation game in which two agents allocate shared resources toward private projects with verifiable jointly optimal outcomes.
  arXiv  Detail & Related papers  (2026-05-03T07:12:14Z)
• InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphs [72.5651722107621]
  InterAgent is an end-to-end framework for text-driven physics-based multi-agent humanoid control.<n>We introduce an autoregressive diffusion transformer equipped with multi-stream blocks, which decouples proprioception, exteroception, and action to cross-modal interference.<n>We also propose a novel interaction graph exteroception representation that explicitly captures fine-grained joint-to-joint spatial dependencies.
  arXiv  Detail & Related papers  (2025-12-08T10:46:01Z)
• VariAntNet: Learning Decentralized Control of Multi-Agent Systems [2.5950969608246797]
  A simple multi-agent system can be effectively utilized in disaster response applications, such as firefighting.<n>These simple robotic agents, also known as Ant Robots, are defined as anonymous agents that possess limited sensing capabilities, lack a shared coordinate system, and do not communicate explicitly with one another.<n>We propose VariAntNet, a deep learning-based decentralized control model designed to facilitate agent swarming and collaborative task execution.
  arXiv  Detail & Related papers  (2025-09-02T12:48:15Z)
• Revisiting Gossip Protocols: A Vision for Emergent Coordination in Agentic Multi-Agent Systems [0.0]
  Gossip protocols offer a missing layer for context-rich, adaptive communication in agentic AI.<n>Gossip enables scalable, low-overhead dissemination of shared knowledge, but also raises unresolved challenges.<n>Gossip is not a silver bullet, but overlooking it risks missing a key path toward resilient, reflexive, and self-organizing multi-agent systems.
  arXiv  Detail & Related papers  (2025-08-03T01:18:58Z)
• Networked Communication for Mean-Field Games with Function Approximation and Empirical Mean-Field Estimation [59.01527054553122]
  Decentralised agents can learn equilibria in Mean-Field Games from a non-episodic run of the empirical system.<n>We introduce function approximation to the existing setting, drawing on the Munchausen Online Mirror Descent method.<n>We show theoretically that exchanging policy information helps networked agents outperform both independent and even centralised agents in function-approximation settings.
  arXiv  Detail & Related papers  (2024-08-21T13:32:46Z)
• Collaborative Optimization of the Age of Information under Partial Observability [34.43476648472727]
  Age of Information (AoI) is the freshness of sensor and control data at the receiver side. We devise a decentralized AoI-minimizing transmission policy for a number of sensor agents sharing capacity-limited, non-FIFO duplex channels. We also leverage mean-field control approximations and reinforcement learning to derive scalable and optimal solutions.
  arXiv  Detail & Related papers  (2023-12-20T12:34:54Z)
• Cooperative Probabilistic Trajectory Forecasting under Occlusion [110.4960878651584]
  Occlusion-aware planning often requires communicating the information of the occluded object to the ego agent for safe navigation. In this paper, we design an end-to-end network that cooperatively estimates the current states of occluded pedestrian in the reference frame of ego agent. We show that the uncertainty-aware trajectory prediction of occluded pedestrian by the ego agent is almost similar to the ground truth trajectory assuming no occlusion.
  arXiv  Detail & Related papers  (2023-12-06T05:36:52Z)
• Distributed Adaptive Learning Under Communication Constraints [54.22472738551687]
  This work examines adaptive distributed learning strategies designed to operate under communication constraints. We consider a network of agents that must solve an online optimization problem from continual observation of streaming data.
  arXiv  Detail & Related papers  (2021-12-03T19:23:48Z)
• Adversarial Attacks On Multi-Agent Communication [80.4392160849506]
  Modern autonomous systems will soon be deployed at scale, opening up the possibility for cooperative multi-agent systems. Such advantages rely heavily on communication channels which have been shown to be vulnerable to security breaches. In this paper, we explore such adversarial attacks in a novel multi-agent setting where agents communicate by sharing learned intermediate representations.
  arXiv  Detail & Related papers  (2021-01-17T00:35:26Z)
• Learning to Communicate and Correct Pose Errors [75.03747122616605]
  We study the setting proposed in V2VNet, where nearby self-driving vehicles jointly perform object detection and motion forecasting in a cooperative manner. We propose a novel neural reasoning framework that learns to communicate, to estimate potential errors, and to reach a consensus about those errors.
  arXiv  Detail & Related papers  (2020-11-10T18:19:40Z)
• Distributed Inference with Sparse and Quantized Communication [7.155594644943642]
  We consider the problem of distributed inference where agents in a network observe a stream of private signals generated by an unknown state. We develop a novel event-triggered distributed learning rule that is based on the principle of diffusing low beliefs on each false hypothesis. We show that by sequentially refining the range of the quantizers, every agent can learn the truth exponentially fast almost surely, while using just $1$ bit to encode its belief on each hypothesis.
  arXiv  Detail & Related papers  (2020-04-02T23:08:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.