CS research tasks on Agentic 200-prompt (held-out test)
0.632Mean@3
Qwen3.5-4B RL on Agentic Self-Instruct data
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| 0.632 | 0.768 | ||
| 0.5 | 0.631 | ||
2026.06 | 0.366 | 0.484 |
Qwen3.5-4B RL on Agentic Self-Instruct data
| Method | Links | ||
|---|---|---|---|
| 0.632 | 0.768 | ||
| 0.5 | 0.631 | ||
2026.06 | 0.366 | 0.484 |