This work develops a theoretical and experimental study of this independent training and cooperative inference paradigm, and establishes classification error guarantees under sufficient, finite-round, and finite-precision communication, together with PAC-style generalization bounds.
Abstract
The increasing heterogeneity of multi-agent systems poses significant challenges for jointly training a global model across agents. At the same time, cooperative inference between agents has long been recognized as a powerful mechanism for distributed decision making over networks. Motivated by these observations, we propose a collaboration framework for distributed binary classification over multi-agent networks, where a set of independently trained agents, potentially differing in architecture, feature space, or modality, coordinate their actions during test time to form collective predictions. This coordination is achieved by exchanging local decision statistics through a distributed learning protocol. We develop a theoretical and experimental study of this independent training and cooperative inference paradigm, and examine its performance under different communication budgets and distributed learning rules. We establish classification error guarantees under sufficient, finite-round, and finite-precision communication, together with PAC-style generalization bounds. These results capture the influence of model heterogeneity, network topology, combination policy, and communication constraints on prediction accuracy. Taken together with the experimental results, they reveal both the price of independent training and the benefit of collective prediction for the proposed distributed decision making framework with models learned from data.
SRPO (Setwise Relative Policy Optimization), which treats the active set the minimal set of outputs consumed by one transition, as one multi-agent action, and unifies division of labor and joint co-evolution as actions with different set sizes.
Sheng-Tian Yang, Zi-Yun Xiong, Yu Li et al.· 4 citations
Distributed large language model infrastructures create fundamentally new semantic attack surfaces involving orchestration layers, retrieval pipelines, autonomous agents, moderation systems, distributed memory components, and adaptive guardrails. Existing adversarial testing methods are inadequate for enterprise-scale...
Sergey I. Serko, A. Petrovski, I. Kotenko· 2026 International Russian A...· 0 citations
Kearns, Roth, and Ryu show that the output agent's error approaches the global predictor's error along sufficiently deep paths with suitable feature coverage, while insufficient depth can prevent aggregation even in large networks.
M. Bateni, Z. Hadizadeh, M. Hajiaghayi et al.· arXiv.org· 0 citations
ICMAPE converts the fixed-confidence identification objective into a reward derived from inference confidence, so that standard reinforcement learning machinery can be applied to decentralized pure exploration.
This work proposes Multi-Agent Flow-Pretrained Policy Optimization (MA-FPPO), which uses online fine-tuning to improve the cooperative behavior of models pretrained with flow matching through new interactions with the environment.
Guo-Wei Zou, Hao-Nan Chen, Hai-Tao Wang et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.