The paper outlines a collaborative intelligence paradigm for LLMs distributed over networks, combining vertical device-cloud and horizontal multi-agent collaboration to deliver high-quality responses under heterogeneous resource constraints.
MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Large Language Models over Networks: Collaborative Intelligence under Resource Constraints
The paper outlines a collaborative intelligence paradigm for LLMs distributed over networks, combining vertical device-cloud and horizontal multi-agent collaboration to deliver high-quality responses under heterogeneous resource constraints.