One-shot path generation raises Validity but lowers Adaptivity and Efficiency relative to step-by-step interaction¶

Claim · All claims
Evidence · 1 study · causal r2 · q2
Currency · newest study 2026 · checked against its sources 2026-10-18 (automated, 1 of 1 entry) · not reviewed by a person

Subclaims¶

q2 i? Static generation increases Validity by 30.8 points for Qwen3-4B-2507 (CoT) but decreases Adaptivity by 28.8 points for Qwen3-30B-A3B (CoT) and Efficiency by 33.8 points for DeepSeek-R1-Distill-14B. → 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? · causal · r2

Comparison of step-by-step interactive planning with one-shot generation of the entire curriculum in a single turn, on Basic Education personas (Table 8). The article reports the printed percentage-point changes; no effect size is printed.

"Static generation increases Validity by 30.8 percentage points for Qwen3-4B-2507 (CoT), while Adaptivity decreases by 28.8 points for Qwen3-30B-A3B (CoT) and Efficiency by 33.8 points for DeepSeek-R1-Distill-14B."

Discussion¶

Related Claims¶

• Adaptivity to individual learners is the primary bottleneck for LLMs in KC path planning — related
• Chain-of-Thought prompting improves KC planning for Qwen models but its effect varies by model and educational stage — related
• Retrieval augmentation raises path Validity but not the joint Final Pass rate — related
• Removing explicit mastery information from learner profiles mainly degrades Adaptivity — related
• Shortest remediation paths respecting attribute prerequisites are shorter than random and full-coverage baseline paths — related