G2CP: A Graph-Grounded Communication Protocol for Verifiable and Efficient Multi-Agent Reasoning
This addresses the challenge of verifiable and efficient coordination in multi-agent systems, particularly for industrial knowledge management, representing a fundamental shift rather than an incremental improvement.
The paper tackled the problem of semantic drift and inefficiency in multi-agent communication by proposing G2CP, a graph-based protocol that reduced communication tokens by 73% and improved task accuracy by 34% in industrial scenarios.
Multi-agent systems powered by Large Language Models face a critical challenge: agents communicate through natural language, leading to semantic drift, hallucination propagation, and inefficient token consumption. We propose G2CP (Graph-Grounded Communication Protocol), a structured agent communication language where messages are graph operations rather than free text. Agents exchange explicit traversal commands, subgraph fragments, and update operations over a shared knowledge graph, enabling verifiable reasoning traces and eliminating ambiguity. We validate G2CP within an industrial knowledge management system where specialized agents (Diagnostic, Procedural, Synthesis, and Ingestion) coordinate to answer complex queries. Experimental results on 500 industrial scenarios and 21 real-world maintenance cases show that G2CP reduces inter-agent communication tokens by 73%, improves task completion accuracy by 34% over free-text baselines, eliminates cascading hallucinations, and produces fully auditable reasoning chains. G2CP represents a fundamental shift from linguistic to structural communication in multi-agent systems, with implications for any domain requiring precise agent coordination. Code, data, and evaluation scripts are publicly available.