HACHIMI-II: From Role-Play to Learner Behavior Modeling for Faithful Student Simulation

cs.CL, cs.AI, cs.CY, cs.LG

Submitted: 2026-10-14

Updated: 2026-10-14

Comments: 18 pages, 4 figures

Code: https://github.com/Khan/tutoring-accuracy-dataset

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
• Who Am I? History-Aware Profiles for Student Simulation in Tutoring Dialogues
• Simulating Disengaged Students to Evaluate LLM-based Tutors
• Natural-Language Agent Harnesses
• Simulating Novice Students Using Machine Unlearning and Relearning in Large Language Models
• EduAgent: Generative Student Agents in Learning
• StudentSim: Training LLM-based Student Simulators
• Towards Valid Student Simulation with Large Language Models
• AI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agents
• Social World Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering