Work

Building a trust-based social agent network

Year: 2026
Type: conference-paper
Abstract: . Agents evolving in a multi-agent system interact with one another to achieve their individual goals. In trust-based agent models, agents form a local view of their environment from their direct interactions, and base their interaction decisions on the trustworthiness of the other agents. Agents can also obtain recommendations about other agents from third parties, either directly or indirectly. Reputation complements trust from direct interactions in providing information for agent selection. While trust and reputation ensure that an agent selects and interacts with the most appropriate provider, we believe that the agent can learn about the agent relationships and interconnections at the same time. By building a network of agents it interacts with, and with information about interaction details, trustworthiness, recommendation chain and reputation, the agent is in a better position to extract emergent information, such as potential new customers, suppliers, its competitors and potentially collusive groups of agents. In this paper we propose a mechanism for agents to build a representation of their local environment based on direct interactions, trust and reputation. 1
Language: English
Open Access status: green
OpenAlex ID: W1943807511
FWCI:
Cites: 18
Cited by: 5
Related to: 10