Tools Fail: Detecting Silent Errors in Faulty Tools
Abstract: Tools have become a mainstay of LLMs, allowing them to retrieve knowledge not in their weights, to perform tasks on the web, and even to control robots. However, most ontologies and surveys of tool-use have assumed the core challenge for LLMs is choosing the tool.
Instead, we introduce a framework for tools more broadly which guides us to explore a model's ability to detect "silent" tool errors, and reflect on how to plan. This more directly aligns with the increasingly popular use of models as tools. We provide an initial approach to failure recovery with promising results both on a controlled calculator setting and embodied agent planning.
Paper Type: Long
Research Area: Language Modeling
Research Area Keywords: prompting,applications,robustness,retrieval-augmented models,multimodality,tool-use
Contribution Types: Model analysis & interpretability, NLP engineering experiment, Data resources, Surveys
Languages Studied: English
Submission Number: 4519
Loading