Goal Detection on ATOD Medium (test)
93.83Goal Detection F1LLM-Rsum
Evaluation Results
| Method | Links | |
|---|---|---|
| LLM-RsumCategory=Memory-based2026.01 | 93.83 | |
| ATOD (Ours)Category=Agentic Memory-based2026.01 | 91.92 | |
| RAGCategory=Memory-based2026.01 | 85.59 | |
| MemoryBankCategory=Memory-based2026.01 | 82.56 | |
| MemoChatCategory=Memory-based2026.01 | 80.38 | |
| Claude-4-SonnetCategory=LLM-based, Prompting=zero-shot2026.01 | 78.95 | |
| Claude-3.7-SonnetCategory=LLM-based, Prompting=zero-shot2026.01 | 76.67 | |
| Claude-3.5-SonnetCategory=LLM-based, Prompting=zero-shot2026.01 | 74.08 | |
| DeepSeek-R1Category=LLM-based, Prompting=zero-shot2026.01 | 52.84 |