BEAGLE: Behavior-Enforced Agent for Grounded Learner Emulation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Hanchen David, Cohn, Clayton, Xu, Zifan, Guo, Siyuan, Biswas, Gautam, Ma, Meiyi
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918485194440704
author Wang, Hanchen David
Cohn, Clayton
Xu, Zifan
Guo, Siyuan
Biswas, Gautam
Ma, Meiyi
author_facet Wang, Hanchen David
Cohn, Clayton
Xu, Zifan
Guo, Siyuan
Biswas, Gautam
Ma, Meiyi
contents Simulating student learning behaviors in open-ended problem-solving environments holds potential for education research, from training adaptive tutoring systems to stress-testing pedagogical interventions. However, collecting authentic data is challenging due to privacy concerns and the high cost of longitudinal studies. While Large Language Models (LLMs) offer a promising path to student simulation, they suffer from competency bias, optimizing for efficient correctness rather than the erratic, iterative struggle characteristic of novice learners. We present BEAGLE, a neuro-symbolic framework that addresses this bias by incorporating Self-Regulated Learning (SRL) theory into a novel architecture. BEAGLE integrates three key technical innovations: (1) a semi-Markov model that governs the timing and transitions of cognitive behaviors and metacognitive behaviors; (2) Bayesian Knowledge Tracing with explicit flaw injection to enforce realistic knowledge gaps and "unknown unknowns"; and (3) a decoupled agent design that separates high-level strategy use from code generation actions to prevent the model from silently correcting its own intentional errors. In evaluations on Python programming tasks, BEAGLE significantly outperforms state-of-the-art baselines in reproducing authentic trajectories. In a human Turing test, participants could not reliably tell BEAGLE traces apart from real student data: classification accuracy was statistically equivalent to chance (52.8%, d' = 0.15, N = 71)
format Preprint
id arxiv_https___arxiv_org_abs_2602_13280
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle BEAGLE: Behavior-Enforced Agent for Grounded Learner Emulation
Wang, Hanchen David
Cohn, Clayton
Xu, Zifan
Guo, Siyuan
Biswas, Gautam
Ma, Meiyi
Artificial Intelligence
Simulating student learning behaviors in open-ended problem-solving environments holds potential for education research, from training adaptive tutoring systems to stress-testing pedagogical interventions. However, collecting authentic data is challenging due to privacy concerns and the high cost of longitudinal studies. While Large Language Models (LLMs) offer a promising path to student simulation, they suffer from competency bias, optimizing for efficient correctness rather than the erratic, iterative struggle characteristic of novice learners. We present BEAGLE, a neuro-symbolic framework that addresses this bias by incorporating Self-Regulated Learning (SRL) theory into a novel architecture. BEAGLE integrates three key technical innovations: (1) a semi-Markov model that governs the timing and transitions of cognitive behaviors and metacognitive behaviors; (2) Bayesian Knowledge Tracing with explicit flaw injection to enforce realistic knowledge gaps and "unknown unknowns"; and (3) a decoupled agent design that separates high-level strategy use from code generation actions to prevent the model from silently correcting its own intentional errors. In evaluations on Python programming tasks, BEAGLE significantly outperforms state-of-the-art baselines in reproducing authentic trajectories. In a human Turing test, participants could not reliably tell BEAGLE traces apart from real student data: classification accuracy was statistically equivalent to chance (52.8%, d' = 0.15, N = 71)
title BEAGLE: Behavior-Enforced Agent for Grounded Learner Emulation
topic Artificial Intelligence
url https://arxiv.org/abs/2602.13280