ToolGate: Contract-Grounded and Verified Tool Execution for LLMs

TL;DR

ToolGate introduces a formal framework for safe and verifiable tool execution in LLMs, ensuring logical safety and trusted state evolution during complex reasoning tasks.

Contribution

It formalizes tool invocation using Hoare-style contracts and maintains a symbolic state to guarantee verifiable and safe tool integration in LLMs.

Findings

Significantly improves reliability of tool-augmented LLMs

Ensures state evolution only through verified tool execution

Maintains competitive performance on reasoning tasks

Abstract

Large Language Models (LLMs) augmented with external tools have demonstrated remarkable capabilities in complex reasoning tasks. However, existing frameworks rely heavily on natural language reasoning to determine when tools can be invoked and whether their results should be committed, lacking formal guarantees for logical safety and verifiability. We present \textbf{ToolGate}, a forward execution framework that provides logical safety guarantees and verifiable state evolution for LLM tool calling. ToolGate maintains an explicit symbolic state space as a typed key-value mapping representing trusted world information throughout the reasoning process. Each tool is formalized as a Hoare-style contract consisting of a precondition and a postcondition, where the precondition gates tool invocation by checking whether the current state satisfies the required conditions, and the postcondition determines whether the tool's result can be committed to update the state through runtime verification. Our approach guarantees that the symbolic state evolves only through verified tool executions, preventing invalid or hallucinated results from corrupting the world representation. Experimental validation demonstrates that ToolGate significantly improves the reliability and verifiability of tool-augmented LLM systems while maintaining competitive performance on complex multi-step reasoning tasks. This work establishes a foundation for building more trustworthy and debuggable AI systems that integrate language models with external tools.