Large Language Models over Networks: Collaborative Intelligence under Resource Constraints
Summary
This paper explores collaborative intelligence paradigms where distributed Large Language Models work together across devices and clouds to handle resource constraints. It covers vertical device-cloud collaboration, horizontal multi-agent collaboration, routing policies, and open research challenges in scalable and trustworthy cooperative AI.
View Cached Full Text
Cached at: 05/13/26, 12:15 PM
Paper page - Large Language Models over Networks: Collaborative Intelligence under Resource Constraints
Source: https://huggingface.co/papers/2605.08626
Abstract
Collaborative intelligence enables multiple distributed LLMs to work together across devices and clouds to provide high-quality responses under diverse resource constraints.
Large language models(LLMs) are transforming society, powering applications from smartphone assistants to autonomous driving. Yet cloud-based LLM services alone cannot serve a growing class of applications, including those operating under intermittent connectivity, sub-second latency budgets, data-residency constraints, or sustained high-volume inference. On-device deployment is in turn constrained by limited computation and memory. No single endpoint can deliver high-quality service across this spectrum. This article focuses oncollaborative intelligence, a paradigm in which multiple independent LLMs distributed across device and cloud endpoints collaborate at the task level through natural language or structured messages. Such collaboration strives for superior response quality under heterogeneous resource constraints spanning computation, memory, communication, and cost across network tiers. We presentcollaborative inferencealong two complementary and composable dimensions: verticaldevice-cloud collaborationand horizontalmulti-agent collaboration, which can be combined into hybrid topologies in practice. We then examine learning to collaborate, addressing the training ofrouting policiesand the development of cooperative capabilities among LLMs. Finally, we identify open research challenges including scaling underresource heterogeneityand trustworthycollaborative intelligence.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2605\.08626
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2605.08626 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2605.08626 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2605.08626 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computing
The paper presents an agentic AI framework that leverages large language models and chain-of-thought reasoning to optimize UAV-assisted logistics scheduling with mobile edge computing, aiming to improve efficiency and resource allocation in manufacturing logistics.
Unleashing the Potential of Large Language Models: A Blueprint for Real-Time, Enterprise-Ready Deployments
This arXiv paper presents a unified LLMOps architecture for real-time, enterprise-ready LLM deployments, integrating data ingestion, continual learning, RAG, and feedback loops. It introduces components like AIPO, STAR+FAR, and SAGE to address knowledge staleness, hallucination, and latency-cost trade-offs in regulated sectors.
Best practices for deploying language models
Cohere, OpenAI, and AI21 Labs have jointly published preliminary best practices for developing and deploying large language models, covering usage guidelines, safety measures, bias mitigation, documentation, diverse teams, and ethical labor standards.
What happens when AI agents get their own collaboration network?
Explores the future of AI agents collaborating in networks, referencing projects like AnvitaFlow and Moltbook, and raises questions about trust and marketplaces for agent services.
Scaling Laws for Hypernetwork-Based Knowledge Injection in Large Language Models
The paper investigates scaling laws for hypernetwork-based knowledge injection into LLMs, finding predictive power law scaling and reliable out-of-distribution generalization, establishing hypernetworks as a scalable alternative to LoRA and full fine-tuning.