When Numbers Start Talking: Implicit Numerical Coordination Among LLM-Based Agents
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Simulation of Random LR Fuzzy Intervals
Random fuzzy variables join the modeling of the impreciseness (due to their ``fuzzy part'') and randomness. Statistical samples of such objects are widely used, and their direct, numerically effective generation is there…
Reflection of Thought: Inversely Eliciting Numerical Reasoning in Language Models via Solving Linear Systems
Numerical reasoning over natural language has been a long-standing goal for the research community. However, cutting-edge language models have proven difficult to reliably generalize to a broad range of numbers, although…
Instruct-NeuralTalker: Editing Audio-Driven Talking Radiance Fields with Instructions
Recent neural talking radiance field methods have shown great success in photorealistic audio-driven talking face synthesis. In this paper, we propose a novel interactive framework that utilizes human instructions to edi…
Face GenerationTalking Face GenerationNumbers Beat Words: A Rigorous On-Premise Benchmark for Coupled MIMO Controller Tuning
Tuning controllers for strongly coupled multi-input multi-output (MIMO) processes is difficult because decentralized auto-tuning ignores loop interaction and local optimization is start-sensitive. We benchmark whether on…
A Computer Vision Based Approach for Stalking Detection Using a CNN-LSTM-MLP Hybrid Fusion Model
Criminal and suspicious activity detection has become a popular research topic in recent years. The rapid growth of computer vision technologies has had a crucial impact on solving this issue. However, physical stalking …
Action DetectionActivity DetectionHead Pose EstimationPose Estimation