Research map / Large language models / Agents, code and math
Learning from Long-Term Engagement: Adaptive Tutoring Dialogue Planning for Personalized Education
Zhiang Dong, Zhenlong Dai, Xiangwei Lv, Jingyuan Chen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add cognitive state extraction (ablation) | LEAP · LEAD Data Structure (session 4) | ROUGE-L: 19.36 -> 21.11 | Improved |
| add cognitive state extraction (ablation) | LEAP · LEAD Data Structure (session 4) | Coherence: 0.708 -> 0.782 | Improved |
| add scaffolding instruction planning (ablation) | LEAP · LEAD Data Structure (session 4) | ROUGE-L: 19.78 -> 21.11 | Improved |
| add scaffolding instruction planning (ablation) | LEAP · LEAD Data Structure (session 4) | Insight: 0.769 -> 0.826 | Improved |
| add direct planner alongside MCTS (ablation) | LEAP · LEAD Data Structure (session 4) | ROUGE-L: 20.25 -> 21.11 | Improved |
| add MCTS planner alongside direct planner (ablation) | LEAP · LEAD Data Structure (session 4) | ROUGE-L: 19.96 -> 21.11 | Improved |
| add MCTS planner alongside direct planner (ablation) | LEAP · LEAD Data Structure (session 4) | Insight: 0.773 -> 0.826 | Improved |
| raise MCTS usage from 52.7% to 100% (ablation) | LEAP · LEAD Data Structure (session 4) | planning precision: 0.872 -> 0.837 | Hurt |
| raise MCTS usage from 52.7% to 100% (ablation) | LEAP · LEAD Data Structure (session 4) | LLM calls: 4,732 -> 7,892 | Hurt |
| use MCTS on 52.7% of cases instead of none (ablation) | LEAP · LEAD Data Structure (session 4) | planning precision: 0.682 -> 0.872 | Improved |
| use LEAP instead of ICL prompting | GPT-4o baseline · LEAD Data Structure (session 4) | ROUGE-L: 19.68 -> 21.11 | Improved |
| use LEAP instead of GPT-4o as tutor | tutoring simulation · LEAD Statistical Analysis | average dialogue turns: 2.45 -> 1.95 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SocraticLM — SocraticLM: Exploring Socratic Personalized Teaching with Large Language Models (NeurIPS 2024) · better on 9 of 9 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- SocraticLM: Exploring Socratic Personalized Teaching with Large Language Models (NeurIPS 2024 · similarity 0.86)
- Conversational Learning Diagnosis via Reasoning Multi-Turn Interactive Learning (AAAI 2026 · similarity 0.86)
- An LLM-Guided Tutoring System for Social Skills Training (AAAI 2025 · similarity 0.86)
- CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs (ICLR 2026 · similarity 0.85)
- StateTree: Enhancing Long-term Dialogue Reasoning via Reinforcement Learning (NeurIPS 2026 · similarity 0.85)
- Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem Solving (ICLR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
