Post-hoc LLM-Supported Debugging of Distributed Processes

TL;DR

This paper introduces a novel AI-assisted debugging approach that uses generative AI to produce natural-language explanations from process data, aiding developers in understanding complex distributed systems more efficiently.

Contribution

The work presents a language-agnostic, AI-supported debugging method that generates natural-language explanations from process data to facilitate easier debugging of distributed systems.

Findings

Demonstrator successfully applied to a Java system

Open-source web application available for use

Approach enhances understanding of complex processes

Abstract

In this paper, we address the problem of manual debugging, which nowadays remains resource-intensive and in some parts archaic. This problem is especially evident in increasingly complex and distributed software systems. Therefore, our objective of this work is to introduce an approach that can possibly be applied to any system, at both the macro- and micro-level, to ease this debugging process. This approach utilizes a system's process data, in conjunction with generative AI, to generate natural-language explanations. These explanations are generated from the actual process data, interface information, and documentation to guide the developers more efficiently to understand the behavior and possible errors of a process and its sub-processes. Here, we present a demonstrator that employs this approach on a component-based Java system. However, our approach is language-agnostic. Ideally, the generated explanations will provide a good understanding of the process, even if developers are not familiar with all the details of the considered system. Our demonstrator is provided as an open-source web application that is freely accessible to all users.