Intelligent Tutoring on Tutoring environment STEM and non-STEM topics (test)
100Success RateOracle
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| OracleScope=BFS, Obs.=GT†, n=3002026.06 | 100 | 0 | 100 | |
| Gemini-Flash OracleScope=Full, Obs.=GT†, n=302026.06 | 100 | 8.4 | 100 | |
| GPT-5-mini OracleScope=Full, Obs.=GT†, n=302026.06 | 100 | 3.4 | 100 | |
| PPOScope=Full, Obs.=Binary, n=3002026.06 | 93.3 | 72.4 | 98.8 | |
| PPO + TutorRLScope=Full, Obs.=NL, n=502026.06 | 82 | 105.6 | 98 | |
| PPO + Qwen2.5Scope=Full, Obs.=NL, n=502026.06 | 78 | 120.1 | 95.4 | |
| Threshold (τ=3)Scope=BFS, Obs.=Binary, n=3002026.06 | 41.7 | 174.9 | 84.6 | |
| RandomScope=Full, Obs.=Binary, n=3002026.06 | 28.3 | 217.4 | 90.6 | |
| Gemini-FlashScope=Full, Obs.=NL, n=302026.06 | 23.3 | 223.3 | 83.9 | |
| GPT-5-miniScope=Full, Obs.=NL, n=302026.06 | 3.3 | 234.2 | 77.1 | |
| Mean kScope=BFS, Obs.=Binary, n=3002026.06 | 0 | 236.2 | 55.6 | |
| ThinkingKT + Qwen2.5Scope=Full, Obs.=NL, n=502026.06 | 0 | 236.2 | 48.1 | |
| ThinkingKT + TutorRLScope=Full, Obs.=NL, n=502026.06 | 0 | 236.2 | 49.3 |