AI RESEARCH
Token Coherence: Adapting MESI Cache Protocols to Minimize Synchronization Overhead in Multi-Agent LLM Systems
arXiv CS.AI
•
ArXi:2603.15183v1 Announce Type: cross Multi-agent LLM orchestration incurs synchronization costs scaling as O(n x S x |D|) in agents, steps, and artifact size under naive broadcast -- a regime I term broadcast-induced triply-multiplicative overhead. I argue this pathology is a structural residue of full-state rebroadcast, not an inherent property of multi-agent coordination.