# AgentCAT: Simulating Computerized Adaptive Testing via Multi-Agent Large Language Models

arXiv: https://arxiv.org/abs/2606.21832 · HTML: https://mlsanity.com/paper/2606.21832/

## Key facts

- No citing papers in the map yet (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 17 of its 47 references that are in the map.
- First posted on arXiv 20 Jun 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, 17 of 17)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents](https://mlsanity.com/paper/2503.01935/) (2025)
- [Simulating Classroom Education with LLM-Empowered Agents](https://mlsanity.com/paper/2406.19226/) (2024)
- [LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation](https://mlsanity.com/paper/2409.20550/) (2024)
- [Knowledge-aware Coupled Graph Neural Network for Social Recommendation](https://mlsanity.com/paper/2110.03987/) (2021)
- [Agent4Edu: Generating Learner Response Data by Generative Agents for Intelligent Education Systems](https://mlsanity.com/paper/2501.10332/) (2025)
- [Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning](https://mlsanity.com/paper/2506.04625/) (2025)
- [BOBCAT: Bilevel Optimization-Based Computerized Adaptive Testing](https://mlsanity.com/paper/2108.07386/) (2021)
- [LLM-powered Multi-agent Framework for Goal-oriented Learning in Intelligent Tutoring System](https://mlsanity.com/paper/2501.15749/) (2025)
- [Quality meets Diversity: A Model-Agnostic Framework for Computerized Adaptive Testing](https://mlsanity.com/paper/2101.05986/) (2021)
- [Simulated patient systems powered by large language model-based AI agents offer potential for transforming medical education](https://mlsanity.com/paper/2409.18924/) (2024)
- [MoocRadar: A Fine-grained and Multi-aspect Knowledge Repository for Improving Cognitive Student Modeling in MOOCs](https://mlsanity.com/paper/2304.02205/) (2023)
- [Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards](https://mlsanity.com/paper/2508.21476/) (2025)
- [Enhancing Cognitive Diagnosis using Un-interacted Exercises: A Collaboration-aware Mixed Sampling Approach](https://mlsanity.com/paper/2312.10110/) (2023)
- [Mapping Student-AI Interaction Dynamics in Multi-Agent Learning Environments: Supporting Personalised Learning and Reducing Performance Gaps](https://mlsanity.com/paper/2506.02993/) (2025)
- [Enhancing Multimodal Entity Linking with Jaccard Distance-based Conditional Contrastive Learning and Contextual Visual Augmentation](https://mlsanity.com/paper/2501.14166/) (2025)
- [Synthesizing High-Quality Programming Tasks with LLM-based Expert and Student Agents](https://mlsanity.com/paper/2504.07655/) (2025)

## Abstract (arXiv)

Computerized Adaptive Testing (CAT), as a key technology for personalized education, aims to accurately assess examinee proficiency by retrieving exercises dynamically matching current ability estimates. However, existing CAT research is constrained by limitations of static offline data and isolated component optimization. Restricted by partial labels in offline logs, researchers degrade the dynamic assessment process into static sequence prediction. Current research focuses on isolated perspectives, e.g., selection or diagnosis, neglecting the overall CAT interaction process. To address this, we propose AgentCAT, a Large Language Model-based multi-agent simulation system, to construct a high-fidelity benchmarking environment for dynamic testing. This framework comprises three modules: (1) The examinee agent with memory retrieval and Chain-of-Thought reasoning simulates responses based on cognitive profiles; (2) The selection agent uses coarse-to-fine bucketing and knowledge graph exploration to balance local difficulty and global coverage; (3) The supervisor uses dual-auditing and robust update to ensure convergence and validity. To validate the framework, we evaluated on two real-world datasets across three dimensions: macro-level ability convergence, micro-level interaction logic, and data sparsity resilience. Results show AgentCAT achieves effective ability estimation, and its selection strategy balances difficulty adaptation and instructional coherence, aligning with human pedagogical intuition.