Fig.1

Concept

Tool memory

Tool memory is a store of reusable execution traces for the tools an agent calls, so it can reproduce or adapt a past invocation instead of re-deriving one from scratch. Think of it like a function cache, except the key is a fuzzy task description and the value is the…

The rest of “Tool memory” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.

Log in to unlock

← Back to the library

Tool memory, explained · Fig. 1