Beyond Text-Passing: Shared Cognitive Substrates for Multi-Agent LLM Coordination

Ning Coeva

Keywords: multi-agent systems, LLM coordination, shared state, coordination primitives, structural continuity

TL;DR: We propose shared cognitive substrates—typed world model, causal graph, and energy pool—as coordination primitives to replace text-passing in multi-agent LLM systems.

Abstract: Current multi-agent LLM systems rely on natural language as the sole medium for inter-agent communication, treating coordination as a message-passing problem. We argue this text-passing bottleneck is a structural limitation—not merely an engineering inconvenience—that fundamentally constrains consistency, efficiency, and auditability. We propose a paradigm shift: from message-passing to shared cognitive substrates, where agents coordinate through three explicit shared primitives: (1) a Shared World Model maintaining typed state with invariants, (2) a Shared Causal Graph representing explicit dependencies and attribution paths, and (3) a Shared Energy Pool enabling resource-aware arbitration under budget constraints. We introduce Baton Arbitration as a coordination mechanism and propose Structural Continuity as an evaluation criterion for system stability. We present this as a blueprint intended to guide the design of substrate-native multi-agent systems.

Submission Number: 36