Aggregation Query Execution on AGGBench
0.456Mean NACEHippoRAG
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| HippoRAGCategory=Single-Step RAG, Base LLM=GPT-4o-mini2026.02 | 0.456 | 0.414 | 2.351 | 0.092 | |
| Naive RAGCategory=Single-Step RAG, Base LLM=GPT-4o-mini2026.02 | 0.533 | 0.45 | 2.327 | 0.008 | |
| smolagentsCategory=Agentic Framework, Base LLM=GPT-4o-mini2026.02 | 0.742 | 0.573 | 2.667 | 0.026 | |
| RATCategory=Multi-Hop RAG, Base LLM=GPT-4o-mini2026.02 | 0.793 | 0.5 | 2.67 | 0.018 | |
| ReActCategory=Agentic Framework, Base LLM=GPT-4o-mini2026.02 | 0.807 | 0.75 | 3.463 | 0.03 | |
| DFACategory=Ours, Base LLM=GPT-4o-mini2026.02 | 0.861 | 0.667 | 3.174 | 0.211 | |
| LightRAGCategory=Single-Step RAG, Base LLM=GPT-4o-mini2026.02 | 1.311 | 0.542 | 3.028 | 0.031 | |
| LLM-onlyCategory=LLM-only, Base LLM=GPT-4o-mini2026.02 | 1.77 | 1 | 3.741 | 0 | |
| Multi-AgentCategory=Agentic Framework, Base LLM=GPT-4o-mini2026.02 | 1.891 | 1 | 5.5 | 0.044 | |
| Single AgentCategory=Agentic Framework, Base LLM=GPT-4o-mini2026.02 | 1.966 | 0.733 | 6.574 | 0.042 | |
| DeepNoteCategory=Multi-Hop RAG, Base LLM=GPT-4o-mini2026.02 | 4.174 | 0.667 | 10.76 | 0.031 |