FREYR: A Framework for Recognizing and Executing Your Requests
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917898718543872 |
|---|---|
| author | Gallotta, Roberto Liapis, Antonios Yannakakis, Georgios N. |
| author_facet | Gallotta, Roberto Liapis, Antonios Yannakakis, Georgios N. |
| contents | Large language models excel as conversational agents, but their capabilities can be further extended through tool usage, i.e.: executable code, to enhance response accuracy or address specialized domains. Current approaches to enable tool usage often rely on model-specific prompting or fine-tuning a model for function-calling instructions. Both approaches have notable limitations, including reduced adaptability to unseen tools and high resource requirements. This paper introduces FREYR, a streamlined framework that modularizes the tool usage process into separate steps. Through this decomposition, we show that FREYR achieves superior performance compared to conventional tool usage methods. We evaluate FREYR on a set of real-world test cases specific for video game design and compare it against traditional tool usage as provided by the Ollama API. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_12423 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FREYR: A Framework for Recognizing and Executing Your Requests Gallotta, Roberto Liapis, Antonios Yannakakis, Georgios N. Software Engineering Artificial Intelligence I.2.1; I.2.7 Large language models excel as conversational agents, but their capabilities can be further extended through tool usage, i.e.: executable code, to enhance response accuracy or address specialized domains. Current approaches to enable tool usage often rely on model-specific prompting or fine-tuning a model for function-calling instructions. Both approaches have notable limitations, including reduced adaptability to unseen tools and high resource requirements. This paper introduces FREYR, a streamlined framework that modularizes the tool usage process into separate steps. Through this decomposition, we show that FREYR achieves superior performance compared to conventional tool usage methods. We evaluate FREYR on a set of real-world test cases specific for video game design and compare it against traditional tool usage as provided by the Ollama API. |
| title | FREYR: A Framework for Recognizing and Executing Your Requests |
| topic | Software Engineering Artificial Intelligence I.2.1; I.2.7 |
| url | https://arxiv.org/abs/2501.12423 |