LLM simulators exhibit near-zero selective response to targeted misconception feedback and behave sycophantically, but SFT and SFS-aligned RL improve this property.
Leveraging generative artificial intelligence to simulate student learning behavior
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
BEAGLE uses a semi-Markov model, Bayesian knowledge tracing with injected flaws, and decoupled strategy-code actions to make LLM agents produce authentic student learning trajectories that humans cannot distinguish from real data at better than chance level.
ArguMath is an AI-simulated classroom environment that enables pre-service math teachers to practice orchestrating mathematical argumentation through customizable scenarios, AI student interactions, and structured reflection, with preliminary user feedback indicating potential benefits for theory-
citing papers explorer
-
Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators
LLM simulators exhibit near-zero selective response to targeted misconception feedback and behave sycophantically, but SFT and SFS-aligned RL improve this property.
-
BEAGLE: Behavior-Enforced Agent for Grounded Learner Emulation
BEAGLE uses a semi-Markov model, Bayesian knowledge tracing with injected flaws, and decoupled strategy-code actions to make LLM agents produce authentic student learning trajectories that humans cannot distinguish from real data at better than chance level.
-
ArguMath: AI-Simulated Environment for Pre-Service Teacher Training in Orchestrating Classroom Mathematics Argumentation
ArguMath is an AI-simulated classroom environment that enables pre-service math teachers to practice orchestrating mathematical argumentation through customizable scenarios, AI student interactions, and structured reflection, with preliminary user feedback indicating potential benefits for theory-