Papers with PORTS
PORTS: Preference-Optimized Retrievers for Tool Selection with Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing retrieval-based methods to pre-select tools are often misaligned with tool-calling LLMs due to separate training processes. |
| Approach: | They propose a method to fine-tune retrievers to find useful tools by using a frozen LLM. |
| Outcome: | The proposed method fine-tunes retrievers to find useful tools using a frozen LLM . it improves tool selection accuracy and can be generalized to new queries and tools . |