GoEX: Perspectives and Designs Towards a Runtime for Autonomous LLM Applications

TL;DR

This paper introduces GoEX, a runtime system that enables safe autonomous LLM applications through post-facto validation, undo features, and damage confinement, reducing human oversight in real-world interactions.

Contribution

The paper presents the design and implementation of GoEX, an open-source runtime that facilitates safe autonomous LLM actions with minimal human supervision.

Findings

GoEX enables effective undo and damage control for LLM actions.

Post-facto validation simplifies verification of LLM outputs.

GoEX supports autonomous interaction with applications with limited human oversight.

Abstract

Large Language Models (LLMs) are evolving beyond their classical role of providing information within dialogue systems to actively engaging with tools and performing actions on real-world applications and services. Today, humans verify the correctness and appropriateness of the LLM-generated outputs (e.g., code, functions, or actions) before putting them into real-world execution. This poses significant challenges as code comprehension is well known to be notoriously difficult. In this paper, we study how humans can efficiently collaborate with, delegate to, and supervise autonomous LLMs in the future. We argue that in many cases, "post-facto validation" - verifying the correctness of a proposed action after seeing the output - is much easier than the aforementioned "pre-facto validation" setting. The core concept behind enabling a post-facto validation system is the integration of an intuitive undo feature, and establishing a damage confinement for the LLM-generated actions as effective strategies to mitigate the associated risks. Using this, a human can now either revert the effect of an LLM-generated output or be confident that the potential risk is bounded. We believe this is critical to unlock the potential for LLM agents to interact with applications and services with limited (post-facto) human involvement. We describe the design and implementation of our open-source runtime for executing LLM actions, Gorilla Execution Engine (GoEX), and present open research questions towards realizing the goal of LLMs and applications interacting with each other with minimal human supervision. We release GoEX at https://github.com/ShishirPatil/gorilla/.