Status Tracking on ATOD Complex (test)
84.28Status Tracking AccuracyATOD (Ours)
Evaluation Results
| Method | Links | |
|---|---|---|
| ATOD (Ours)Category=Agentic Memory-based2026.01 | 84.28 | |
| Claude-4-SonnetCategory=LLM-based, Prompting=zero-shot2026.01 | 84.26 | |
| Claude-3.7-SonnetCategory=LLM-based, Prompting=zero-shot2026.01 | 78.64 | |
| MemoryBankCategory=Memory-based2026.01 | 78.5 | |
| RAGCategory=Memory-based2026.01 | 77.83 | |
| Claude-3.5-SonnetCategory=LLM-based, Prompting=zero-shot2026.01 | 76.1 | |
| DeepSeek-R1Category=LLM-based, Prompting=zero-shot2026.01 | 74.42 | |
| LLM-RsumCategory=Memory-based2026.01 | 69.95 | |
| MemoChatCategory=Memory-based2026.01 | 66.83 |