Combining Cognitive and Generative AI for Self-explanation in Interactive AI Agents

TL;DR

This paper explores integrating cognitive and generative AI to enable interactive AI agents like VERA to self-explain their reasoning, enhancing transparency in complex ecological modeling and simulation environments.

Contribution

It introduces a novel approach combining cognitive and generative AI for self-explanation in interactive agents, using a TMK model and ChatGPT-based explanation generation.

Findings

Preliminary evaluation shows promising explanation quality.

Combines cognitive modeling with generative AI for transparency.

Demonstrates potential for improved user understanding in ecological simulations.

Abstract

The Virtual Experimental Research Assistant (VERA) is an inquiry-based learning environment that empowers a learner to build conceptual models of complex ecological systems and experiment with agent-based simulations of the models. This study investigates the convergence of cognitive AI and generative AI for self-explanation in interactive AI agents such as VERA. From a cognitive AI viewpoint, we endow VERA with a functional model of its own design, knowledge, and reasoning represented in the Task--Method--Knowledge (TMK) language. From the perspective of generative AI, we use ChatGPT, LangChain, and Chain-of-Thought to answer user questions based on the VERA TMK model. Thus, we combine cognitive and generative AI to generate explanations about how VERA works and produces its answers. The preliminary evaluation of the generation of explanations in VERA on a bank of 66 questions derived from earlier work appears promising.