Subscribe
Topic

Tool Use

How LLMs and AI agents call tools and functions. Posts compare open function-calling models like Gorilla, Hermes 3 and xLAM, explain tool-call failure recovery, and weigh executable code actions against JSON tool calling.

Articles

1-3
  1. Open-Source Function-Calling Models in Production: Comparing Gorilla OpenFunctions-v2, Hermes 3, Functionary, and xLAM

    Deploying autonomous AI agents and automated API workflows requires reliable structured output generation and tool invocation. While general-purpose language models can be prompted to output JSON tool invocations, specialized function-calling fine-tunes provide higher schema compliance, lower parameter hallucination rates, and support for parallel tool invocation. Four open-source model families have emerged as prominent architectures for local and private function calling: Gorilla OpenFunction

    AI
    4 min read
  2. Tool-Call Failure Recovery in Production AI Agents: Syntactic Repair, Schema Coercion, Parameter Inoculation, and Dynamic Fallback Architectures

    Tool-Call Failure Recovery in Production AI Agents: Syntactic Repair, Schema Coercion, Parameter Inoculation, and Dynamic Fallback Architectures Autonomous language model agents operate by interleaving natural language reasoning traces with structured tool invocations. However, when deployed in multi-turn production environments, raw tool calling exhibits significant fragility. Empirical studies from benchmark suites such as $\tau$-bench (arXiv:2406.12045) and the Berkeley Function Calling Lead

    Agents
    8 min read