| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Symbolic Reasoning | Letter | Accuracy92.4 | 33 | |
| Classification | LETTER (test) | Accuracy87.1 | 33 | |
| LTL Instruction Following | Letter Finite-horizon (full) | Success Rate (SR)100 | 19 | |
| Multiclass classification | letter (test) | Log Loss (Posterior)0.2656 | 18 | |
| LTL Instruction Following | Letter Infinite-horizon (full) | µAcc7.13 | 10 | |
| LTL-guided Reinforcement Learning | Letter Finite-horizon (test) | Success Rate (SR)100 | 9 | |
| Classification | Letter pi+=0.8 UCI (test) | Accuracy97.6 | 9 | |
| Classification | Letter pi+=0.5 UCI (test) | Accuracy97.5 | 9 | |
| Classification | Letter (pi+=0.2) UCI (test) | Accuracy97.8 | 9 | |
| Continual Clustering | Letter | AI NMI57.1 | 8 | |
| Outlier Detection | letter (1600, 32) (full) | Recall33 | 7 | |
| Binary Classification | letter LIBSVM (test) | Average AUC0.811 | 7 | |
| Classification | LETTER (10-fold cross-val) | Test F1 Score65.9 | 7 | |
| Off-Policy Evaluation | Letter (UCI) | MSE0.0018 | 6 | |
| Classification | LETTER | Empirical Risk0.25 | 6 | |
| Active Learning Classification | Letter | Total Regret2,571 | 6 | |
| Missing Data Imputation | Letter | RMSE0.1198 | 6 | |
| LTL-guided Reinforcement Learning | Letter Infinite-horizon (test) | µAcc7.13 | 5 | |
| Clustering | Letter | Time0.33 | 5 | |
| Pairwise Learning | letter (test) | Average AUC81.1 | 5 | |
| Multiclass Classification | letter | Accuracy97.4 | 2 | |
| LTL-guided Reinforcement Learning | Letter Infinite-horizon v1 (test) | µacc- | 0 | |
| LTL Instruction Following | Letter Infinite-horizon | µAcc- | 0 | |
| LTL Instruction Following | Letter Finite-horizon v1 (test) | Success Rate- | 0 | |
| Symbolic Reasoning | Letter 4 | Accuracy- | 0 |