Query Routing for Homogeneous Tools: An Instantiation in the RAG Scenario
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917790359748608 |
|---|---|
| author | Mu, Feiteng Jiang, Yong Zhang, Liwen Liu, Chu Li, Wenjie Xie, Pengjun Huang, Fei |
| author_facet | Mu, Feiteng Jiang, Yong Zhang, Liwen Liu, Chu Li, Wenjie Xie, Pengjun Huang, Fei |
| contents | Current research on tool learning primarily focuses on selecting the most effective tool from a wide array of options, often overlooking cost-effectiveness, a crucial factor in human problem-solving. In this paper, we address the selection of homogeneous tools by predicting both their performance and the associated cost required to accomplish a given task. We then assign queries to the optimal tools in a cost-effective manner. Our experimental results demonstrate that our method achieves higher performance at a lower cost compared to strong baseline approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_12429 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Query Routing for Homogeneous Tools: An Instantiation in the RAG Scenario Mu, Feiteng Jiang, Yong Zhang, Liwen Liu, Chu Li, Wenjie Xie, Pengjun Huang, Fei Artificial Intelligence Current research on tool learning primarily focuses on selecting the most effective tool from a wide array of options, often overlooking cost-effectiveness, a crucial factor in human problem-solving. In this paper, we address the selection of homogeneous tools by predicting both their performance and the associated cost required to accomplish a given task. We then assign queries to the optimal tools in a cost-effective manner. Our experimental results demonstrate that our method achieves higher performance at a lower cost compared to strong baseline approaches. |
| title | Query Routing for Homogeneous Tools: An Instantiation in the RAG Scenario |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2406.12429 |