aiqbench analysis
This research introduces UCO, a reinforcement learning framework that enables large language models to act as adaptive tutors by distinguishing genuine student comprehension from rote echoing. By incorporating real-time cognitive state perception and dynamic reward functions based on the Zone of Proximal Development, the method allows LLMs to tailor teaching strategies effectively during multi-turn interactions. The approach demonstrates superior performance over existing baselines in math tutoring benchmarks, marking a significant step toward truly intelligent educational agents.
UCO: A Multi-Turn Interactive Reinforcement Learning Method for Adaptive Teaching with Large Language Models
arXiv:2511.08873v3 Announce Type: replace Abstract: Large language models (LLMs) are shifting from answer providers to intelligent tutors in educational settings, yet current supervised fine-tuning methods only learn surface teaching patterns without dynamic adaptation capabilities. Recent reinforcement learning approaches address this limitation but face two critical challenges. First, they evaluate teaching effectiveness solely based on whether students produce correct outputs, unable to distinguish whether students genuinely understand or echo teacher-provided answers during interaction. Second, they cannot perceive students' evolving cognitive states in real time through interactive dialogue, thus failing to adapt teaching strategies to match students' cognitive levels dynamically. We propose the Unidirectional Cognitive Optimization (UCO) method to address these challenges. UCO uses a multi-turn interactive reinforcement learning paradigm where the innovation lies in two synergistic reward functions: the Progress Reward captures students' cognitive advancement, evaluating whether students truly transition from confusion to comprehension, while the Scaffold Reward dynamically identifies each student's Zone of Proximal Development (ZPD), encouraging teachers to maintain productive teaching within this zone. We evaluate UCO by comparing it against 11 baseline models on BigMath and MathTutorBench benchmarks. Experimental results demonstrate that our UCO model outperforms all models of equivalent scale and achieves performance comparable to advanced closed-source models. The code and data are available at https://github.com/Mind-Lab-ECNU/UCO.
Abstract:Large language models (LLMs) are shifting from answer providers to intelligent tutors in educational settings, yet current supervised fine-tuning methods only learn surface teaching patterns without dynamic adaptation capabilities. Recent reinforcement learning approaches address this limitation but face two critical challenges. First, they evaluate teaching effectiveness solely based on whether students produce correct outputs, unable to distinguish whether students genuinely understand or echo teacher-provided answers during interaction. Second, they cannot perceive students' evolving cognitive states in real time through interactive dialogue, thus failing to adapt teaching strategies to match students' cognitive levels dynamically. We propose the Unidirectional Cognitive Optimization (UCO) method to address these challenges. UCO uses a multi-turn interactive reinforcement learning paradigm where the innovation lies in two synergistic reward functions: the Progress Reward captures students' cognitive advancement, evaluating whether students truly transition from confusion to comprehension, while the Scaffold Reward dynamically identifies each student's Zone of Proximal Development (ZPD), encouraging teachers to maintain productive teaching within this zone. We evaluate UCO by comparing it against 11 baseline models on BigMath and MathTutorBench benchmarks. Experimental results demonstrate that our UCO model outperforms all models of equivalent scale and achieves performance comparable to advanced closed-source models. The code and data are available at this https URL.
Artificial Intelligence (cs.AI)
arXiv:2511.08873 [cs.AI]
(or arXiv:2511.08873v3 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2511.08873 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 298 words
Related coverage
The art and science of hyperparameter optimization on Amazon Nova Forge
AWS · Jun 2, 2026
2026 BAIR Graduate Showcase
BAIR Blog · Jul 1, 2026
Synthetic document finetuning for instilling positive traits
AI Alignment Forum · Jun 16, 2026
The Machines that Make the Machines
NVIDIA · Oct 7, 2026