← All concepts

tool calling architecture

3 articles · 15 co-occurring · 1 contradictions · 0 briefs

Explains tool calling as context expansion mechanism—allows LLM to 'think about' more via tool availability signaling

@jonas: It also goes through another unnecessary JSON or xml encoding for LLM "tool c...

Author argues current JSON/XML tool-calling approach adds unnecessary overhead; proposes direct code streaming as alternative

Explains tool calling as context expansion mechanism—allows LLM to 'think about' more via tool availability signaling

Author argues current JSON/XML tool-calling approach adds unnecessary overhead; proposes direct code streaming as alternative

Article directly addresses how to structure tool definitions for optimal agent reasoning and selection accuracy.

query this concept
$ db.articles("tool-calling-architecture")
$ db.cooccurrence("tool-calling-architecture")
$ db.contradictions("tool-calling-architecture")