An Approach to Joint Hybrid Decision Making between Humans and Artificial Intelligence

2025-11-29

AI Summary

This study addresses the challenges of authority allocation and capability integration in human–machine heterogeneous agent collaborative decision-making. Methodologically, it introduces the Joint Hybrid Intelligence (JHI) framework—the first to formally define a general agent decision-making model and a joint design space—integrating human factors engineering, AI engineering, and interaction design to establish novel collaboration paradigms (e.g., “extended swarms”) and realize distributed human–machine decision integration via joint agent engineering. Theoretically, it establishes the first systematic, scalable theory framework and design architecture for human–machine collaborative decision-making. Empirical evaluation demonstrates significant improvements in decision efficiency, robustness, and human controllability across complex tasks, validating both the framework’s effectiveness and its cross-domain applicability.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent/AI Theories and Architectures

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
• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation

Abstract

Due to the progress in artificial intelligence, it is important to understand how capable artificial agents should be used when interacting with humans, since high level authority and responsibility often remain with the human agent. However, integrated frameworks are lacking that can account for heterogeneous agents and draw on different scientific fields, such as human-factors engineering and artificial intelligence. Therefore, joint hybrid intelligence is described as a framework abstracting humans and artificial intelligence as decision making agents. A general definition of intelligence is provided on the basis of decision making competence being applicable to agents of different sorts. This framework is used for proposing the interrelated design space of joint hybrid intelligence being aimed at integrating the heterogeneous capabilities of humans and artificial intelligence. At the core of this design space lies joint agent engineering with the goal of integrating the design subspaces operator training, artificial intelligence engineering, and interface design via developing joint agent patterns. The ''extended swarming'' approach to human-swarm interaction is discussed as an example of such a pattern.

Problem

• Develop a framework for human-AI joint decision-making
• Integrate heterogeneous capabilities of humans and artificial intelligence
• Propose a design space for joint agent engineering

Innovation

• Joint hybrid intelligence framework for human-AI decision making
• Design space integrating heterogeneous capabilities via agent engineering
• Extended swarming pattern as example for human-swarm interaction