Learning to Collaborate: An Orchestrated-Decentralized Framework for Peer-to-Peer LLM Federation

• URL: http://arxiv.org/abs/2601.17133v1
• Date: Fri, 23 Jan 2026 19:18:43 GMT
• Title: Learning to Collaborate: An Orchestrated-Decentralized Framework for Peer-to-Peer LLM Federation
• Authors: Inderjeet Singh, Eleonore Vissol-Gaudin, Andikan Otung, Motoyoshi Sekiya,
• Abstract summary: This paper introduces KNEXA-FL, a novel framework for orchestrated decentralization.<n>It employs a non-aggregating Central Profiler/Matchmaker that formulates P2P collaboration as a contextual bandit problem.<n>Our experiments show that KNEXA-FL yields substantial gains, improving Pass@1 by approx. 50% relative to random P2P collaboration.
• Score: 0.9231476323484774
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Fine-tuning Large Language Models (LLMs) for specialized domains is constrained by a fundamental challenge: the need for diverse, cross-organizational data conflicts with the principles of data privacy and sovereignty. While Federated Learning (FL) provides a framework for collaboration without raw data exchange, its classic centralized form introduces a single point of failure and remains vulnerable to model inversion attacks. Decentralized FL (DFL) mitigates this risk by removing the central aggregator but typically relies on inefficient, random peer-to-peer (P2P) pairings, forming a collaboration graph that is blind to agent heterogeneity and risks negative transfer. This paper introduces KNEXA-FL, a novel framework for orchestrated decentralization that resolves this trade-off. KNEXA-FL employs a non-aggregating Central Profiler/Matchmaker (CPM) that formulates P2P collaboration as a contextual bandit problem, using a LinUCB algorithm on abstract agent profiles to learn an optimal matchmaking policy. It orchestrates direct knowledge exchange between heterogeneous, PEFT-based LLM agents via secure distillation, without ever accessing the models themselves. Our comprehensive experiments on a challenging code generation task show that KNEXA-FL yields substantial gains, improving Pass@1 by approx. 50% relative to random P2P collaboration. Critically, our orchestrated approach demonstrates stable convergence, in stark contrast to a powerful centralized distillation baseline which suffers from catastrophic performance collapse. Our work establishes adaptive, learning-based orchestration as a foundational principle for building robust and effective decentralized AI ecosystems.

Related papers

• A Secure and Private Distributed Bayesian Federated Learning Design [56.92336577799572]
  Distributed Federated Learning (DFL) enables decentralized model training across large-scale systems without a central parameter server.<n>DFL faces three critical challenges: privacy leakage from honest-but-curious neighbors, slow convergence due to the lack of central coordination, and vulnerability to Byzantine adversaries aiming to degrade model accuracy.<n>We propose a novel DFL framework that integrates Byzantine robustness, privacy preservation, and convergence acceleration.
  arXiv  Detail & Related papers  (2026-02-23T16:12:02Z)
• Scaling Decentralized Learning with FLock [31.883271929012977]
  This paper introduces FLock, a decentralized framework for fine-tuning large language models (LLMs)<n> Integrating a blockchain-based trust layer with economic incentives, FLock replaces the central aggregator with a secure, auditable protocol for cooperation among untrusted parties.<n>Our experiments show the FLock framework defends against backdoor poisoning attacks that compromise standard FLs.
  arXiv  Detail & Related papers  (2025-07-21T08:01:43Z)
• UnifyFL: Enabling Decentralized Cross-Silo Federated Learning [0.0]
  We develop a trust-based cross-silo Federated Learning framework called UnifyFL.<n>Our evaluation on a diverse testbed shows that UnifyFL achieves a performance comparable to the ideal multilevel centralized FL.
  arXiv  Detail & Related papers  (2025-04-26T13:15:40Z)
• Decentralized Directed Collaboration for Personalized Federated Learning [39.29794569421094]
  We concentrate on the Decentralized Personalized Learning (DPFL) that performs distributed training model computation. We propose a directed collaboration framework by incorporating textbfDecentralized textbfFederated textbfPartial textbfGradient textbfPedGP.
  arXiv  Detail & Related papers  (2024-05-28T06:52:19Z)
• Decentralized Federated Policy Gradient with Byzantine Fault-Tolerance and Provably Fast Convergence [21.935405256685307]
  In Federated Reinforcement Learning (FRL), agents aim to collaboratively learn a common task, while each agent is acting in its local environment without exchanging raw trajectories. We first propose a new centralized Byzantine fault-tolerant policy (PG) algorithm that improves existing methods by relying only on assumptions standard for non-fault-tolerant PG.
  arXiv  Detail & Related papers  (2024-01-07T14:06:06Z)
• DFedADMM: Dual Constraints Controlled Model Inconsistency for Decentralized Federated Learning [52.83811558753284]
  Decentralized learning (DFL) discards the central server and establishes a decentralized communication network. Existing DFL methods still suffer from two major challenges: local inconsistency and local overfitting.
  arXiv  Detail & Related papers  (2023-08-16T11:22:36Z)
• Towards More Suitable Personalization in Federated Learning via Decentralized Partial Model Training [67.67045085186797]
  Almost all existing systems have to face large communication burdens if the central FL server fails. It personalizes the "right" in the deep models by alternately updating the shared and personal parameters. To further promote the shared parameters aggregation process, we propose DFed integrating the local Sharpness Miniization.
  arXiv  Detail & Related papers  (2023-05-24T13:52:18Z)
• Combating Exacerbated Heterogeneity for Robust Models in Federated Learning [91.88122934924435]
  Combination of adversarial training and federated learning can lead to the undesired robustness deterioration. We propose a novel framework called Slack Federated Adversarial Training (SFAT) We verify the rationality and effectiveness of SFAT on various benchmarked and real-world datasets.
  arXiv  Detail & Related papers  (2023-03-01T06:16:15Z)
• Blockchain Assisted Decentralized Federated Learning (BLADE-FL): Performance Analysis and Resource Allocation [119.19061102064497]
  We propose a decentralized FL framework by integrating blockchain into FL, namely, blockchain assisted decentralized federated learning (BLADE-FL) In a round of the proposed BLADE-FL, each client broadcasts its trained model to other clients, competes to generate a block based on the received models, and then aggregates the models from the generated block before its local training of the next round. We explore the impact of lazy clients on the learning performance of BLADE-FL, and characterize the relationship among the optimal K, the learning parameters, and the proportion of lazy clients.
  arXiv  Detail & Related papers  (2021-01-18T07:19:08Z)
• F2A2: Flexible Fully-decentralized Approximate Actor-critic for Cooperative Multi-agent Reinforcement Learning [110.35516334788687]
  Decentralized multi-agent reinforcement learning algorithms are sometimes unpractical in complicated applications. We propose a flexible fully decentralized actor-critic MARL framework, which can handle large-scale general cooperative multi-agent setting. Our framework can achieve scalability and stability for large-scale environment and reduce information transmission.
  arXiv  Detail & Related papers  (2020-04-17T14:56:29Z)

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.