# Investigating Pedagogical Teacher and Student LLM Agents: Genetic Adaptation Meets Retrieval Augmented Generation Across Learning Style

arXiv: https://arxiv.org/abs/2505.19173 · HTML: https://mlsanity.com/paper/2505.19173/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation.
- Builds on 13 of its 40 references that are in the map.
- First posted on arXiv 25 May 2025.

## Placed in

- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)
- 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, 13 of 13)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future](https://mlsanity.com/paper/2309.15402/) (2023)
- [RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation](https://mlsanity.com/paper/2404.00610/) (2024)
- [Simulating Classroom Education with LLM-Empowered Agents](https://mlsanity.com/paper/2406.19226/) (2024)
- [CGMI: Configurable General Multi-Agent Interaction Framework](https://mlsanity.com/paper/2308.12503/) (2023)
- [Exploiting Cognitive Structure for Adaptive Learning](https://mlsanity.com/paper/1905.12470/) (2019)
- [One Size doesn't Fit All: A Personalized Conversational Tutoring Agent for Mathematics Instruction](https://mlsanity.com/paper/2502.12633/) (2025)
- [Off the Beaten Path: Let's Replace Term-Based Retrieval with k-NN Search](https://mlsanity.com/paper/1610.10001/) (2016)
- [TutorUp: What If Your Students Were Simulated? Training Tutors to Address Engagement Challenges in Online Learning](https://mlsanity.com/paper/2502.16178/) (2025)
- [Explainable Few-shot Knowledge Tracing](https://mlsanity.com/paper/2405.14391/) (2024)
- [Take a Break in the Middle: Investigating Subgoals towards Hierarchical Script Generation](https://mlsanity.com/paper/2305.10907/) (2023)

## Built on by (most cited first, 4 of 4)

- [Investigating Learner-Aware Design of LLM-Generated Educational Feedback](https://mlsanity.com/paper/2602.11650/) (2026)
- [EduPersona: Benchmarking Subjective Ability Boundaries of Virtual Student Agents](https://mlsanity.com/paper/2510.04648/) (2025)
- [When Does Defendant Statement Matter? A Study of Bias and Persuasion in LLM-Simulated Jurors](https://mlsanity.com/paper/2609.09887/) (2026)
- [How Well Can LLMs Simulate Real Learner Evaluations of Educational Feedback?](https://mlsanity.com/paper/2609.35376/) (2026)

## Abstract (arXiv)

Effective teaching requires adapting instructional strategies to accommodate the diverse cognitive and behavioral profiles of students, a persistent challenge in education and teacher training. While Large Language Models (LLMs) offer promise as tools to simulate such complex pedagogical environments, current simulation frameworks are limited in two key respects: (1) they often reduce students to static knowledge profiles, and (2) they lack adaptive mechanisms for modeling teachers who evolve their strategies in response to student feedback. To address these gaps, we introduce a novel simulation framework that integrates LLM-based heterogeneous student agents with a self-optimizing teacher agent. The teacher agent's pedagogical policy is dynamically evolved using a genetic algorithm, allowing it to discover and refine effective teaching strategies based on the aggregate performance of diverse learners. In addition, we propose Persona-RAG, a Retrieval Augmented Generation module that enables student agents to retrieve knowledge tailored to their individual learning styles. Persona-RAG preserves the retrieval accuracy of standard RAG baselines while enhancing personalization, an essential factor in modeling realistic educational scenarios. Through extensive experiments, we demonstrate how our framework supports the emergence of distinct and interpretable teaching patterns when interacting with varied student populations. Our results highlight the potential of LLM-driven simulations to inform adaptive teaching practices and provide a testbed for training human educators in controlled, data-driven environments.