# PersonaPath: Towards Knowledge-Centric Personalized Learning Path Planning

arXiv: https://arxiv.org/abs/2609.18861 · HTML: https://mlsanity.com/paper/2609.18861/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 45 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Builds on (most cited first, 13 of 13)

- [PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change](https://mlsanity.com/paper/2206.10498/) (2022)
- [Deep Knowledge Tracing](https://mlsanity.com/paper/1506.05908/) (2015)
- [Large Language Models for Generative Information Extraction: A Survey](https://mlsanity.com/paper/2312.17617/) (2023)
- [A Self-Attentive model for Knowledge Tracing](https://mlsanity.com/paper/1907.06837/) (2019)
- [Dynamic Key-Value Memory Networks for Knowledge Tracing](https://mlsanity.com/paper/1611.08108/) (2016)
- [Exploiting Cognitive Structure for Adaptive Learning](https://mlsanity.com/paper/1905.12470/) (2019)
- [Enhancing Item Response Theory for Cognitive Diagnosis](https://mlsanity.com/paper/1905.10957/) (2019)
- [Bringing Generative AI to Adaptive Learning in Education](https://mlsanity.com/paper/2402.14601/) (2024)
- [AppBench: Planning of Multiple APIs from Various APPs for Complex User Instruction](https://mlsanity.com/paper/2410.19743/) (2024)
- [ToolSpectrum : Towards Personalized Tool Utilization for Large Language Models](https://mlsanity.com/paper/2505.13176/) (2025)
- [Constructing a personalized learning path using genetic algorithms approach](https://mlsanity.com/paper/2104.11276/) (2021)
- [Quantifying the Capability Boundary of DeepSeek Models: An Application-Driven Performance Analysis](https://mlsanity.com/paper/2502.11164/) (2025)
- [Are Large Language Models Effective Knowledge Graph Constructors?](https://mlsanity.com/paper/2510.11297/) (2025)

## Abstract (arXiv)

Adaptive learning systems commonly formulate learning path planning as Exercise-Centric (EC) recommendation, where the next step is inferred from item-level interaction logs. Evaluating goal-oriented guidance additionally requires explicit learner goals and curriculum-scale prerequisites: learners with similar exercise records may need different paths toward their targets. We therefore study Knowledge-Centric (KC) personalized learning path planning, where a planner must reason over learner profiles, mastery states, and prerequisite knowledge structures to decide which textbook, unit, and concept should be studied next. To support this setting, we introduce PersonaPath, a benchmark that pairs 2,000 fine-grained learner personas with a hierarchical knowledge graph of 347 textbooks, 1,751 units, and 4,092 concepts across 77 subjects. We evaluate representative LLMs on PersonaPath. Results show that even the strongest LLM reaches only a 29.5% final pass rate in Basic Education, and that the main bottleneck lies in adaptivity, where no model exceeds 44.7% in tailoring paths to individual learners.