Toward a Computational Theory of Evidence-Based Reasoning for Instructable Cognitive Agents
This work addresses the need for more adaptable and teachable AI systems in critical domains like government and public sector, though it appears incremental as it builds on existing research in cognitive agents.
The paper tackles the problem of developing instructable cognitive agents for evidence-based reasoning tasks by proposing a computational theory, and demonstrates its application through four prototype agents in government and public sector domains, including intelligence analysis, science education, cybersecurity, and intelligence, surveillance, and reconnaissance.
Evidence-based reasoning is at the core of many problem-solving and decision-making tasks in a wide variety of domains. Generalizing from the research and development of cognitive agents in several such domains, this paper presents progress toward a computational theory for the development of instructable cognitive agents for evidence-based reasoning tasks. The paper also illustrates the application of this theory to the development of four prototype cognitive agents in domains that are critical to the government and the public sector. Two agents function as cognitive assistants, one in intelligence analysis, and the other in science education. The other two agents operate autonomously, one in cybersecurity and the other in intelligence, surveillance, and reconnaissance. The paper concludes with the directions of future research on the proposed computational theory.