Not just for humans: Explanation for agent-to-agent communication

Once precisely defined so as to include just the explanation's act, the notion of explanation should be regarded as a central notion in the engineering of intelligent system—not just as an add-on to make them understandable to humans. Based on symbolic AI techniques to match intuitive and rational cognition, explanation should be exploited as a fundamental tool for inter-agent communication among heterogeneous agents in open multi-agent systems. More generally, explanation-ready agents should work as the basic components in the engineering of intelligent systems integrating both symbolic and sub-/non-symbolic AI techniques.

Talk given at AIxIA 2020 Discussion Paper Workshop, AI*IA 2020 (reboot), 27 November 2020.

Record on APICe: https://talks.apice.unibo.it/ExplanationAixia2020dp