G2CP: A Graph-Grounded Communication Protocol for Verifiable and Efficient Multi-Agent Reasoning

2026-02-13

AI Summary

This work addresses the challenges of natural language–based communication in multi-agent systems, which often leads to semantic drift, hallucination propagation, and high communication overhead. To mitigate these issues, the authors propose a graph-structured communication protocol that, for the first time, shifts agent interactions from unstructured free text to structured operations over a shared knowledge graph—specifically, graph traversal instructions, subgraph exchanges, and update commands. This approach enables verifiable, unambiguous, and auditable collaborative reasoning. Experimental results in industrial settings demonstrate a 73% reduction in communication tokens, a 34% improvement in task accuracy, complete elimination of cascading hallucinations, and the generation of fully traceable reasoning chains.

Technology Category

• Multiagent Systems: Agent Communication
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Agentic search

Abstract

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.

Problem

• multi-agent systems
• semantic drift
• hallucination propagation
• communication efficiency
• natural language communication

Innovation

• Graph-Grounded Communication
• Multi-Agent Reasoning
• Structured Communication Protocol
• Knowledge Graph
• Verifiable Reasoning