arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.13370cs.MAcs.AIcs.CL
收藏

G2CP:一种基于图的可验证和高效的多智能体推理通信协议

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

University of Lorraine, LORIA(洛林大学,LORIA)

Karim Ben Khaled, Davy Monticolo

AI总结:

G2CP通过图操作实现多智能体高效、可验证的推理通信,提升任务准确率并消除幻觉传播。

摘要:

大型语言模型驱动的多智能体系统面临关键挑战:智能体通过自然语言交流,导致语义漂移、幻觉传播和低效的token消耗。我们提出G2CP(图基础通信协议),一种结构化的智能体通信语言,其中信息是图操作而非自由文本。智能体在共享知识图上交换显式遍历命令、子图片段和更新操作,实现可验证的推理轨迹并消除歧义。我们验证了G2CP在工业知识管理系统中的有效性,其中专门的智能体(诊断、程序、合成和摄入)协调回答复杂查询。在500个工业场景和21个现实世界维护案例上的实验结果表明,G2CP减少了智能体间通信token的73%,比自由文本基线提高了34%的任务完成准确率,消除了级联幻觉,并生成完全可审计的推理链。G2CP代表了多智能体系统从语言到结构通信的根本转变,对任何需要精确智能体协调的领域都有影响。代码、数据和评估脚本已公开可用。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑