FREYR: A Framework for Recognizing and Executing Your Requests
Roberto Gallotta, Antonios Liapis, Georgios N. Yannakakis

TL;DR
FREYR is a modular framework that enhances large language models' ability to recognize and execute tool-based requests, outperforming traditional methods in real-world video game design scenarios.
Contribution
The paper introduces FREYR, a novel modular framework that improves tool usage in language models by decomposing the process into separate steps, increasing adaptability and performance.
Findings
FREYR outperforms traditional tool usage methods in test cases.
FREYR demonstrates superior performance in real-world video game design tasks.
Modularization enhances flexibility and effectiveness of tool integration.
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsBusiness Process Modeling and Analysis · Service-Oriented Architecture and Web Services
MethodsSparse Evolutionary Training
