Paper Detail
Liangqi Yuan, Wenzhi Fang, Shiqiang Wang, H. Vincent Poor, Christopher G. Brinton
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 on collaborative 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 present collaborative inference along two complementary and composable dimensions: vertical device-cloud collaboration and horizontal multi-agent collaboration, which can be combined into hybrid topologies in practice. We then examine learning to collaborate, addressing the training of routing policies and the development of cooperative capabilities among LLMs. Finally, we identify open research challenges including scaling under resource heterogeneity and trustworthy collaborative intelligence.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{yuan2026large,
title = {Large Language Models over Networks: Collaborative Intelligence under Resource Constraints},
author = {Liangqi Yuan and Wenzhi Fang and Shiqiang Wang and H. Vincent Poor and Christopher G. Brinton},
year = {2026},
abstract = {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 thi},
url = {https://huggingface.co/papers/2605.08626},
keywords = {large language models, collaborative intelligence, device-cloud collaboration, multi-agent collaboration, collaborative inference, routing policies, resource heterogeneity, huggingface daily},
eprint = {2605.08626},
archiveprefix = {arXiv},
}
{}