Abstract
Tool-augmented large language models extend their capabilities beyond parametric knowledge through external tools, but tend to invoke them unnecessarily. We investigate whether tool-use decisions have any stable internal representation that can be extracted and manipulated, a question that is non-trivial given that tools exist entirely in context at inference time and have no direct encoding in model weights.
We show that steering vectors extracted from heading-anchor positions exert bidirectional causal control over tool-invocation behavior across five open-source models and three domains, suppressing unnecessary tool use most effectively in domains where parametric reasoning suffices.
However, geometric analysis reveals that this causal effectiveness does not correspond to clean linear structure: tool-invocation steps exhibit diffuse, bimodal alignment with the suppression vector rather than the consistent negative alignment a linear encoding account would predict, and different tool types recruit largely distinct internal signatures with low cross-tool feature overlap.
We hypothesize these geometric properties are indicative of the non-parametric nature of tools, and distinguish tool-use steering vectors from those extracted for parametrically grounded concepts. The relationship between this geometric irregularity and the observed causal effectiveness remains an open question.
Blogger's Review: This paper reveals the complexities of tool usage, especially in large language models. Through an in-depth analysis of steering vectors, the authors not only demonstrate the intrinsic mechanisms of tool invocation but also introduce a new geometric perspective, providing rich insights for future research. Understanding these properties will aid in optimizing tool usage strategies, thus enhancing model effectiveness and efficiency.