提出可验证的智能体间通信协议，确保术语理解一致。
Verifiable Semantics for Agent-to-Agent Communication
- 基于刺激-意义模型，通过可观测事件测试术语一致性
- 核心保护推理使分歧降低72%-96%，语言模型验证降51%
- 支持漂移检测与词汇重协商，适合高可靠性多智能体系统
多智能体系统需要一致的通信，但缺乏验证智能体是否共享相同术语理解的方法。自然语言可解释但易产生语义漂移，学习型协议高效却不透明。本文提出基于刺激-意义模型的认证协议：智能体在共享可观测事件上接受测试，若实证分歧低于统计阈值，则术语被认证。在仅使用认证术语进行推理（核心保护推理）的设定下，分歧可被严格限制。同时提出漂移检测（重新认证）和词汇恢复（重协商）机制。仿真中，核心保护使分歧降低72%-96%；在微调语言模型上的验证中，分歧减少51%。该框架为可验证的智能体间通信迈出关键一步。
原文摘要 · Abstract (English)
Multiagent AI systems require consistent communication, but we lack methods to verify that agents share the same understanding of the terms used. Natural language is interpretable but vulnerable to semantic drift, while learned protocols are efficient but opaque. We propose a certification protocol based on the stimulus-meaning model, where agents are tested on shared observable events and terms are certified if empirical disagreement falls below a statistical threshold. In this protocol, agents restricting their reasoning to certified terms ("core-guarded reasoning") achieve provably bounded disagreement. We also outline mechanisms for detecting drift (recertification) and recovering shared vocabulary (renegotiation). In simulations with varying degrees of semantic divergence, core-guarding reduces disagreement by 72-96%. In a validation with fine-tuned language models, disagreement is reduced by 51%. Our framework provides a first step towards verifiable agent-to-agent communication.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。