AI RESEARCH
A Token/KV-Cache Communication Media Selection and Resource Allocation Strategy for Multi-Agent Collaboration
arXiv CS.AI
•
ArXi:2605.25422v1 Announce Type: cross The convergence of large language models (LLMs) with 6G networks is fostering a paradigm of autonomous multi-agent cooperation, which in turn is expected to substantially increase east-west traffic. Although latent-space interaction mechanisms can enable efficient collaboration than symbolic natural-language (NL) exchanges, prior work often abstracts away the associated communication overhead under practical wireless constraints.