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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhong, Renyi, Huo, Yintong, Gu, Wenwei, Li, Yichen, Lyu, Michael R.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911283390971904
author Zhong, Renyi
Huo, Yintong
Gu, Wenwei
Li, Yichen
Lyu, Michael R.
author_facet Zhong, Renyi
Huo, Yintong
Gu, Wenwei
Li, Yichen
Lyu, Michael R.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18528
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle End-to-End Automated Logging via Multi-Agent Framework
Zhong, Renyi
Huo, Yintong
Gu, Wenwei
Li, Yichen
Lyu, Michael R.
Software Engineering
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.
title End-to-End Automated Logging via Multi-Agent Framework
topic Software Engineering
url https://arxiv.org/abs/2511.18528