Adaptivity to individual learners is the primary bottleneck for LLMs in KC path planning¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2026 · checked against its sources 2026-10-20 (automated, 1 of 1 entry) · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly

Subclaims¶

q2 i? Models perform relatively well on Validity (DeepSeek-V3.1 at 90.9%) but no model exceeds 44.7% on Adaptivity in Basic Education. → Yu Liu 2026

Evidence¶

Yu Liu 2026¶

Yu Liu, Zeming Liu, Tianle Zhang, Zihao Cheng, Yuhang Guo, Kehai Chen, Min Zhang, Yunhong Wang, Haifeng Wang. (2026). PersonaPath: Towards Knowledge-Centric Personalized Learning Path Planning. arXiv. https://arxiv.org/abs/2609.18861 doi:10.48550/arxiv.2609.18861

q2 · i? · design · r2

Results section analysis of Table 4 pass rates across the three evaluation dimensions. The article reports DeepSeek-V3.1's Validity pass rate at 90.9% while Adaptivity remains the bottleneck, with the top Adaptivity rate at 44.7% for Qwen3-30B-A3B (CoT) and 44.3% for DeepSeek-V3.1. No effect size is printed.

"Adaptivityremains the primary bottleneck: even the top-performing Qwen3-30B-A3B (CoT) achieves only 44.7%, while DeepSeek-V3.1 reaches 44.3%. This reveals a gap in personalization"

Discussion¶

Related Claims¶

• Strongest LLMs reach only about 29.5% final pass rate on Basic Education KC planning and drop to 14.6% on Higher Education — related
• One-shot path generation raises Validity but lowers Adaptivity and Efficiency relative to step-by-step interaction — related
• Chain-of-Thought prompting improves KC planning for Qwen models but its effect varies by model and educational stage — related
• Removing explicit mastery information from learner profiles mainly degrades Adaptivity — a narrower finding that bears on this claim
• Retrieval augmentation raises path Validity but not the joint Final Pass rate — related