Intelligent Tutoring Systems (ITSs) have shown great potential in enhancing how education is delivered. Many existing ITSs leverage Reinforcement Learning (RL) to optimize the sequence of exercises proposed to the learner. These systems adapt content based on the student's performance on previous exercises, addressing knowledge gaps while advancing through mastered concepts. However, they typically operate at the whole-exercise level, without visibility into the intermediate steps. In reality, learners may fail to solve an exercise because they encounter difficulties with specific sub-steps. Existing ITSs rely on datasets that do not include exercise decomposition in steps. To overcome this limitation, in this paper, we employ GPT-o3-mini to generate synthetic step-by-step solutions for mathematics exercises from the Junyi Academy dataset. To evaluate if these synthetic steps are useful in reaching the final solution, we use three models of varying size from the Llama family to simulate students of different knowledge levels (i.e., low, medium, high) and verify if the step-by-step guidance increases their problem-solving capabilities. By comparing direct answers for exercises to answers that leverage an incremental step guidance strategy, models successfully solve up to 42\% more exercises. This evaluation serves as a foundation for creating synthetic step-by-step solutions that can be employed to develop next-generation step-aware ITSs tailored to students' specific knowledge gaps.

Towards Step-Aware ITSs: Generation and Evaluation of Synthetic Step-by-Step Exercise Solutions / Russo, Francesca; Calo, Tommaso; De Russis, Luigi. - (2025), pp. 281-285. (Intervento presentato al convegno L@S '25: Twelfth ACM Conference on Learning @ Scale tenutosi a Palermo (ITA) nel 21-23 July 2025) [10.1145/3698205.3733940].

Towards Step-Aware ITSs: Generation and Evaluation of Synthetic Step-by-Step Exercise Solutions

Russo, Francesca;Calo, Tommaso;De Russis, Luigi
2025

Abstract

Intelligent Tutoring Systems (ITSs) have shown great potential in enhancing how education is delivered. Many existing ITSs leverage Reinforcement Learning (RL) to optimize the sequence of exercises proposed to the learner. These systems adapt content based on the student's performance on previous exercises, addressing knowledge gaps while advancing through mastered concepts. However, they typically operate at the whole-exercise level, without visibility into the intermediate steps. In reality, learners may fail to solve an exercise because they encounter difficulties with specific sub-steps. Existing ITSs rely on datasets that do not include exercise decomposition in steps. To overcome this limitation, in this paper, we employ GPT-o3-mini to generate synthetic step-by-step solutions for mathematics exercises from the Junyi Academy dataset. To evaluate if these synthetic steps are useful in reaching the final solution, we use three models of varying size from the Llama family to simulate students of different knowledge levels (i.e., low, medium, high) and verify if the step-by-step guidance increases their problem-solving capabilities. By comparing direct answers for exercises to answers that leverage an incremental step guidance strategy, models successfully solve up to 42\% more exercises. This evaluation serves as a foundation for creating synthetic step-by-step solutions that can be employed to develop next-generation step-aware ITSs tailored to students' specific knowledge gaps.
2025
979-8-4007-1291-3
File in questo prodotto:
File Dimensione Formato  
2025_las_wip.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Creative commons
Dimensione 612.07 kB
Formato Adobe PDF
612.07 kB Adobe PDF Visualizza/Apri
2025_las_wip_editorial.pdf

accesso riservato

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 1.06 MB
Formato Adobe PDF
1.06 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/3000468