Re:Optimizing Tool Selection for LLM Workflows with Differen...
by viksit on Sunday July 06, 2025 @12:16AM
(#44477802)
+1 - the biggest issue is not being able to fine tune the llm to learn the specifics of how to make a tool call better over time, which an approach like this can bring to the table.
I guess that applies when you're not able to fine-tune the LLM you're using. Presumably Anthropic has a lot of data too.