TrueReason: An Exemplar Personalised Learning System Integrating Reasoning with Foundational Models

• DOI: 10.48550/arxiv.2502.10411
• Publication Date: 2025-01-23
• Authors: Sahan Bulathwela; Daniel van Niekerk; Jarrod Shipton; María Pérez‐Ortiz; Benjamin Rosman; John Shawe‐Taylor
• Keywords: FOS: Computer and information sciences; Computer Science - Computation and Language; I.2.4; Computer Science - Artificial Intelligence; I.2.6; I.2.4; I.2.7; H.3.3; I.2.6; K.3.1; I.2.7; K.3.1; Computer Science - Information Retrieval; Computer Science - Computers and Society; Artificial Intelligence (cs.AI); H.3.3; Computers and Society (cs.CY); Computer Science - Multiagent Systems; Computation and Language (cs.CL); Information Retrieval (cs.IR); Multiagent Systems (cs.MA)

Personalised education is one of the domains that can greatly benefit from most recent advances in Artificial Intelligence (AI) and Large Language Models (LLM). However, it also challenging applications due to cognitive complexity teaching effectively while personalising learning experience suit independent learners. We hypothesise promising approach excelling such demanding use cases using a \emph{society minds}. In this chapter, we present TrueReason, an exemplar personalised system integrates multitude specialised AI models mimic micro skills are composed together by LLM operationalise planning reasoning. The architecture initial prototype presented describing two have been incorporated prototype. proposed demonstrates first step building sophisticated systems take up very complex tasks demanded as education.