Mistral Patent for "Code implemented tool calls"

Mistral AI has been granted a patent for a method that uses a large language model (LLM) to generate code blocks encapsulating tool calls, which are executed in a sandbox with the ability to pause for user input, according to a patent filing. The method involves receiving a user request, generating a code block via the LLM, executing it in a sandbox, pausing on pending tool calls to transmit them to a client for execution, and resuming with the results. This innovation could enhance AI-driven automation by enabling more interactive and controlled tool execution.

CPC 2013.01 G06F 9/547 | 20 Claims | 1. A method, comprising:receiving, at a server, a user request for execution of one or more tool calls; generating, by a large language model LLM , a code block in a programming language, the code block configured to encapsulate the one or more tool calls; executing, by the server, the code block in a sandbox; in response to obtaining a pending tool call, pausing execution of the code block; transmitting the pending tool call to a client for execution; receiving, from the client, a first result of the pending tool call; resuming execution of the code block and substituting the first result of the pending tool call for the pending tool call in the code block; and returning a second result of the executed code block to the LLM. |