# BEAGLE: Behavior-Enforced Agent for Grounded Learner Emulation

arXiv: https://arxiv.org/abs/2602.13280 · HTML: https://mlsanity.com/paper/2602.13280/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Educational agents and math problem solving, one of 16 directions in LLM agents and tool use.
- Builds on 28 of its 64 references that are in the map.
- First posted on arXiv 6 Feb 2026.

## Placed in

- LLM agents and tool use / [Educational agents and math problem solving](https://mlsanity.com/agents/educational-agents-and-math-problem-solving/)

## Builds on (most cited first, 28 of 28)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Understanding the Effects of RLHF on LLM Generalisation and Diversity](https://mlsanity.com/paper/2310.06452/) (2023)
- [Character-LLM: A Trainable Agent for Role-Playing](https://mlsanity.com/paper/2310.10158/) (2023)
- [Quantifying the Persona Effect in LLM Simulations](https://mlsanity.com/paper/2402.10811/) (2024)
- [Recursive Introspection: Teaching Language Model Agents How to Self-Improve](https://mlsanity.com/paper/2407.18219/) (2024)
- [EKT: Exercise-aware Knowledge Tracing for Student Performance Prediction](https://mlsanity.com/paper/1906.05658/) (2019)
- [Systematic Biases in LLM Simulations of Debates](https://mlsanity.com/paper/2402.04049/) (2024)
- [CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations](https://mlsanity.com/paper/2310.11501/) (2023)
- [Generative Students: Using LLM-Simulated Student Profiles to Support Question Item Evaluation](https://mlsanity.com/paper/2405.11591/) (2024)
- [Translating a Math Word Problem to an Expression Tree](https://mlsanity.com/paper/1811.05632/) (2018)
- [EduAgent: Generative Student Agents in Learning](https://mlsanity.com/paper/2404.07963/) (2024)
- [Agent4Edu: Generating Learner Response Data by Generative Agents for Intelligent Education Systems](https://mlsanity.com/paper/2501.10332/) (2025)
- [Towards the Pedagogical Steering of Large Language Models for Tutoring: A Case Study with Modeling Productive Failure](https://mlsanity.com/paper/2410.03781/) (2024)
- [Can LLMs Reliably Simulate Human Learner Actions? A Simulation Authoring Framework for Open-Ended Learning Environments](https://mlsanity.com/paper/2410.02110/) (2024)
- [Leveraging generative artificial intelligence to simulate student learning behavior](https://mlsanity.com/paper/2310.19206/) (2023)
- [Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation](https://mlsanity.com/paper/2502.02780/) (2025)
- [Privacy-Preserving Synthetic Educational Data Generation](https://mlsanity.com/paper/2207.03202/) (2022)
- [Do LLMs Make Mistakes Like Students? Exploring Natural Alignment between Language Models and Human Error Patterns](https://mlsanity.com/paper/2502.15140/) (2025)
- [LLM-itation is the Sincerest Form of Data: Generating Synthetic Buggy Code Submissions for Computing Education](https://mlsanity.com/paper/2411.10455/) (2024)
- [A Theory of Adaptive Scaffolding for LLM-Based Pedagogical Agents](https://mlsanity.com/paper/2508.01503/) (2025)
- [Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction](https://mlsanity.com/paper/2512.18880/) (2025)
- [Towards Valid Student Simulation with Large Language Models](https://mlsanity.com/paper/2601.05473/) (2026)
- [CoderAgent: Simulating Student Behavior for Personalized Programming Learning with Large Language Models](https://mlsanity.com/paper/2505.20642/) (2025)
- [Evidence-Decision-Feedback: Theory-Driven Adaptive Scaffolding for LLM Agents](https://mlsanity.com/paper/2602.01415/) (2026)
- [DrawSim-PD: Simulating Student Science Drawings to Support NGSS-Aligned Teacher Diagnostic Reasoning](https://mlsanity.com/paper/2602.01578/) (2026)

## Built on by (most cited first, 1 of 1)

- [From Mastery Profile to Simulated Response: Stochastic Student Knowledge Graphs (SSKG) for Faithful LLM Student Simulation](https://mlsanity.com/paper/2608.21668/) (2026)

## Abstract (arXiv)

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)