Informace o publikaci
Mutual Influence AI: Trust-Based Cooperation Mechanisms for LLM Multi-Agent Systems
| Autoři | |
|---|---|
| Rok publikování | 2025 |
| Druh | Článek v odborném periodiku |
| Časopis / Zdroj | Advances in Electrical and Electronic Engineering |
| Fakulta / Pracoviště MU | |
| Citace | |
| Klíčová slova | Mutual influence; multi-agent systems; large language models; AutoGen |
| Popis | This paper introduces Mutual Influence AI, a novel concept for adaptive cooperation in multi-agent systems. Unlike classical independent reasoning or centralized orchestration, our approach introduces an explicit mutual influence factor µ that captures trust adjusted peer feedback and directly modulates large language model (LLM) generation. We present (i) a mathematical formalization of mutual influence, (ii) a prototype implementation integrated with Microsoft AutoGen for LLM-based agents, and (iii) qualitative evi- dence that the framework improves adaptability, transparency, and coordination in multi-agent dialogues. Results show that Mutual Influence AI stabilizes group interactions efficiently while providing interpretable control over how agents influence each other. This positions Mutual Influence AI as a new paradigm for LLM-driven multi-agent systems with potential applications ranging from collaborative problem solving to cybersecurity. Quantitatively, across 167 simulation runs, cross–role agreement increased from 0.19 (base-line) to 0.50 under influence (approx. +160%), with median revision depth (approx. 1.0). Under adversarial feedback, agreement still improved (0.18 to 0.47). |
| Související projekty: |