Ev-Trust: A Strategy Equilibrium Trust Mechanism for Evolutionary Games in LLM-Based Multi-Agent Services
🤖 AI Summary
To address deception, fraud, and misinformation propagation arising from decentralization and heterogeneity in LLM-driven open multi-agent service systems, this paper proposes a dynamic feedback mechanism integrating direct trust, indirect trust, and expected utility. Grounded in evolutionary game theory and replicator dynamics, we design a distributed “request–response–payment–evaluation” service framework and theoretically establish the existence and local asymptotic stability of its evolutionary equilibrium. Our key contributions are (i) autonomous exclusion of malicious agents and (ii) self-reinforcement of high-quality collaboration. Experiments demonstrate a significant improvement in trust assessment accuracy: the proportion of malicious strategies decreases by 32.7%, while system-wide collective utility increases by 28.4%.
Application Category
📝 Abstract
The rapid evolution of the Web toward an agent-centric paradigm, driven by large language models (LLMs), has enabled autonomous agents to reason, plan, and interact in complex decentralized environments. However, the openness and heterogeneity of LLM-based multi-agent systems also amplify the risks of deception, fraud, and misinformation, posing severe challenges to trust establishment and system robustness. To address this issue, we propose Ev-Trust, a strategy-equilibrium trust mechanism grounded in evolutionary game theory. This mechanism integrates direct trust, indirect trust, and expected revenue into a dynamic feedback structure that guides agents' behavioral evolution toward equilibria. Within a decentralized "Request-Response-Payment-Evaluation" service framework, Ev-Trust enables agents to adaptively adjust strategies, naturally excluding malicious participants while reinforcing high-quality collaboration. Furthermore, our theoretical derivation based on replicator dynamics equations proves the existence and stability of local evolutionary equilibria. Experimental results indicate that our approach effectively reflects agent trustworthiness in LLM-driven open service interaction scenarios, reduces malicious strategies, and increases collective revenue. We hope Ev-Trust can provide a new perspective on trust modeling for the agentic service web in group evolutionary game scenarios.
Problem
Research questions and friction points this paper is trying to address.
Addresses trust issues in LLM-based multi-agent systems
Mitigates deception and fraud risks in decentralized agent interactions
Establishes stable trust equilibria using evolutionary game theory
Innovation
Methods, ideas, or system contributions that make the work stand out.
Evolutionary game theory trust mechanism
Dynamic feedback integrating trust and revenue
Decentralized service framework excluding malicious agents
🔎 Similar Papers
No similar papers found.
