Culture-Based Explainable Human-Agent Deconfliction
This addresses the need for accountable and explainable AI in human-agent systems to enhance trust and acceptance, particularly in resource-contested scenarios, though it is incremental in applying argumentation methods to a specific domain.
The paper tackles the problem of enabling AI agents to operate under human norms by proposing an argumentation-based architecture that maps regulations into a culture for agents, with explainable behavior validated through a user study in path deconfliction, showing that explanations significantly improve human performance and reduce perceived challenge in complex systems.
Law codes and regulations help organise societies for centuries, and as AI systems gain more autonomy, we question how human-agent systems can operate as peers under the same norms, especially when resources are contended. We posit that agents must be accountable and explainable by referring to which rules justify their decisions. The need for explanations is associated with user acceptance and trust. This paper's contribution is twofold: i) we propose an argumentation-based human-agent architecture to map human regulations into a culture for artificial agents with explainable behaviour. Our architecture leans on the notion of argumentative dialogues and generates explanations from the history of such dialogues; and ii) we validate our architecture with a user study in the context of human-agent path deconfliction. Our results show that explanations provide a significantly higher improvement in human performance when systems are more complex. Consequently, we argue that the criteria defining the need of explanations should also consider the complexity of a system. Qualitative findings show that when rules are more complex, explanations significantly reduce the perception of challenge for humans.