大模型代理在无直接沟通时仍能通过隐性信号协作
When Numbers Start Talking: Implicit Numerical Coordination Among LLM-Based Agents
- 设计四类博弈场景，对比显性、受限与无沟通下的协作机制
- 发现即使无语言交流，代理也能通过行为模式形成隐性协调
- 适用于研究多智能体系统中非语言协作的场景
基于大模型的代理在多代理环境中日益普遍，需具备战略互动与协调能力。现有研究多关注单个代理或有显式通信的代理交互，较少探讨无显式沟通下的隐性协调。本文通过博弈论方法，研究大模型驱动的多代理系统中的隐性通信。在四种经典的博弈设定下，分析了显式、受限及无沟通条件下的交互表现，考虑代理个性差异以及一次性与重复性博弈，揭示了隐性信号何时出现及其如何影响协调与策略结果。
原文摘要 · Abstract (English)
LLMs-based agents increasingly operate in multi-agent environments where strategic interaction and coordination are required. While existing work has largely focused on individual agents or on interacting agents sharing explicit communication, less is known about how interacting agents coordinate implicitly. In particular, agents may engage in covert communication, relying on indirect or non-linguistic signals embedded in their actions rather than on explicit messages. This paper presents a game-theoretic study of covert communication in LLM-driven multi-agent systems. We analyse interactions across four canonical game-theoretic settings under different communication regimes, including explicit, restricted, and absent communication. Considering heterogeneous agent personalities and both one-shot and repeated games, we characterise when covert signals emerge and how they shape coordination and strategic outcomes.
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。