End-to-End Automated Logging via Multi-Agent Framework

TL;DR

Autologger is a comprehensive framework that automates software logging by accurately deciding when to log and intelligently generating log statements, significantly improving logging quality and generalizability across projects.

Contribution

The paper introduces Autologger, a hybrid end-to-end framework with a novel classifier and multi-agent system for automated logging, addressing fundamental logging decisions and composite logging challenges.

Findings

Achieves 96.63% F1-score on whether-to-log classification.

Improves overall logging quality by 16.13% over baselines.

Demonstrates strong generalizability across different LLMs.

Abstract

Software logging is critical for system observability, yet developers face a dual crisis of costly overlogging and risky underlogging. Existing automated logging tools often overlook the fundamental whether-to-log decision and struggle with the composite nature of logging. In this paper, we propose Autologger, a novel hybrid framework that addresses the complete the end-to-end logging pipeline. Autologger first employs a fine-tuned classifier, the Judger, to accurately determine if a method requires new logging statements. If logging is needed, a multi-agent system is activated. The system includes specialized agents: a Locator dedicated to determining where to log, and a Generator focused on what to log. These agents work together, utilizing our designed program analysis and retrieval tools. We evaluate Autologger on a large corpus from three mature open-source projects against state-of-the-art baselines. Our results show that Autologger achieves 96.63\% F1-score on the crucial whether-to-log decision. In an end-to-end setting, Autologger improves the overall quality of generated logging statements by 16.13\% over the strongest baseline, as measured by an LLM-as-a-judge score. We also demonstrate that our framework is generalizable, consistently boosting the performance of various backbone LLMs.