LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error

arXiv:2403.04746v1 Announce Type: cross
Abstract: Tools are essential for large language models (LLMs) to acquire up-to-date information and take consequential actions in external environments. Existing work on tool-augmented LLMs primarily focuses on the broad coverage of tools and the flexibility of adding new tools. However, a critical aspect that has surprisingly been understudied is simply how accurately an LLM uses tools for which it has been trained. We find that existing LLMs, including GPT-4 and open-source LLMs specifically fine-tuned for …

abstract arxiv augmented llms coverage cs.ai cs.cl cs.lg environments error flexibility however information language language models large language large language models llms through tool tools type work