Zum Inhalt springen
KI-Atlas

Werkzeug- und Funktionsaufruf

Das Modell wählt die API und füllt die Argumente

Agenten & WerkzeugnutzungFortgeschritten #35
EingabeTextAktion

Der vollständige Artikel liegt auf Englisch vor; Titel und Zusammenfassung sind lokalisiert.

WAS DIESE FÄHIGKEIT BEDEUTET

Takes a user request and a list of available tools — names, descriptions, argument schemas — and outputs a structured call such as get_weather with city set to Shanghai. The model executes nothing itself; it selects a tool and assembles arguments, while the actual call is made by external code whose result is fed back for further reasoning.

Wie sie technisch umgesetzt wird

Fine-tuning on many examples of when to call, which tool to use and what arguments look like teaches the model to emit a call when it needs external information or action; at inference the tool definitions go into the prompt and the output is constrained to a valid structure. With many tools, retrieval first narrows the candidates, and a multi-turn loop that feeds results back handles complex tasks.

Repräsentative Produkte

10

Beteiligte Organisationen

Typische Verwendungen

  • Fetching live data such as weather, prices or stock
  • Performing business actions such as orders and messages
  • Calling calculators, search and code executors
  • Chaining several APIs for a composite task

Wie sie bewertet wird

Function-selection accuracy
Share of requests where the right tool was chosen
Exact argument match
Share with arguments exactly matching the reference
End-to-end task success
Whether the task completes once tools actually run

Grenzen und schwierige Punkte

  • Slightly complex argument shapes — nested objects, arrays, optional fields — are easily filled wrongly
  • As the tool list grows, wrong selections rise sharply, and similar-purpose tools are the most confusable
  • Recovery after a failed call is unreliable, and the model often loops on the error instead of adapting

Konzepte dahinter