Multi-Agent Systems for Information Systems Research: A Multi-Agent Systems for Information Systems Research: A Framework for Collaborative AI-Augmented Inquiry Framework for Collaborative AI-Augmented Inquiry

Token-Efficient Multi-Agent Collaboration via System One-Guided Computational Division of Labor

Large language model (LLM)-based multi-agent systems (MAS) have become a promising paradigm for complex information-seeking and reasoning tasks by enabling collaborative problem solving among specialized agents. However, existing MAS frameworks tightly couple task reasoning with coordination operations, including task...

Autonomous AI agents and recursive self-improvement: a comprehensive survey of contemporary architectures, capabilities, and safety frameworks

BusMA: A Bus Communication Substrate for Multi-Agent Systems

This work proposes BusMA, a communication framework that allows any agent to address other agents through a shared channel, i.e., the Bus, which consists of agent registration, message routing, and shared memory management components.

From Language Models to Agentic AI: A Survey of Autonomous, Action-Enabled, and Collaborative LLM Agents

A unified, taxonomy-driven, and deployment-oriented survey of agentic AI systems, synthesizing recent advances through a modular reference architecture and a four-dimensional taxonomy that characterizes agents along the axes of autonomy, tool use, collaboration, and safety–governance is presented.

Toward User-Orchestrated Human–Multi-Agent Teams for Co-Creation

It is argued that creative co-creation calls instead for user-orchestrated Human–Multi-Agent Teams (HMATs), teams in which humans participate alongside multiple agents while retaining the ability to keep the team aligned with the evolving purposes of the work.

Multi-Agent Systems – Issues, Design and Challenges