From Conversation to Orchestration: HCI Challenges and Opportunities in Interactive Multi-Agentic Systems

2025-06-24

AI Summary

This paper addresses the lack of human-computer interaction (HCI) research on multi-agent systems (e.g., AutoGen, OpenAI Swarm), which are increasingly deployed yet poorly understood from a human-centered perspective. We systematically analyze their architectural characteristics and user collaboration challenges by synthesizing existing frameworks, case studies, and design examples—identifying core issues including coordination mechanisms, conflict resolution, user control, transparency, and trust. Based on this analysis, we propose an HCI research framework comprising collaborative models, interaction patterns, and design principles, outlining concrete, scalable research directions. Our key contribution lies in shifting beyond the traditional single-agent paradigm to model multi-agent interaction as a user-centered collaborative process. This fosters interdisciplinary dialogue and provides theoretical foundations and practical guidelines for designing trustworthy, controllable, and explainable multi-agent systems. (149 words)

Technology Category

• Multiagent Systems: Coordination and Collaboration
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Human-Computer Interaction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Recent advances in multi-agentic systems (e.g. AutoGen, OpenAI Swarm) allow users to interact with a group of specialised AI agents rather than a single general-purpose agent. Despite the promise of this new paradigm, the HCI community has yet to fully examine the opportunities, risks, and user-centred challenges it introduces. We contribute to research on multi-agentic systems by exploring their architectures and key features through a human-centred lens. While literature and use cases remain limited, we build on existing tools and frameworks available to developers to identify a set of overarching challenges, e.g. orchestration and conflict resolution, that can guide future research in HCI. We illustrate these challenges through examples, offer potential design considerations, and provide research opportunities to spark interdisciplinary conversation. Our work lays the groundwork for future exploration and offers a research agenda focused on user-centred design in multi-agentic systems.

Problem

• Exploring HCI challenges in multi-agentic systems interaction
• Identifying orchestration and conflict resolution issues in AI agents
• Proposing user-centred design research for multi-agentic systems

Innovation

• Human-centred multi-agent system architectures
• Orchestration and conflict resolution techniques
• User-centred design research agenda