# LogSieve: Task-Aware CI Log Reduction for Sustainable LLM-Based Analysis

arXiv: https://arxiv.org/abs/2601.20148 · HTML: https://mlsanity.com/paper/2601.20148/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 51 references that are in the map.
- First posted on arXiv 28 Jan 2026.

## Builds on (most cited first, 20 of 20)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Green AI](https://mlsanity.com/paper/1907.10597/) (2019)
- [Carbon Emissions and Large Neural Network Training](https://mlsanity.com/paper/2104.10350/) (2021)
- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [GPTScore: Evaluate as You Desire](https://mlsanity.com/paper/2302.04166/) (2023)
- [Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning](https://mlsanity.com/paper/2002.05651/) (2020)
- [RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models](https://mlsanity.com/paper/2310.16340/) (2023)
- [Exploring LLM-based Agents for Root Cause Analysis](https://mlsanity.com/paper/2403.04123/) (2024)
- [A Survey on Automated Log Analysis for Reliability Engineering](https://mlsanity.com/paper/2009.07237/) (2020)
- [Logzip: Extracting Hidden Structures via Iterative Clustering for Log Compression](https://mlsanity.com/paper/1910.00409/) (2019)
- [LogShrink: Effective Log Compression by Leveraging Commonality and Variability of Log Data](https://mlsanity.com/paper/2309.09479/) (2023)
- [A Comprehensive Survey of Logging in Software: From Logging Statements Automation to Log Mining and Analysis](https://mlsanity.com/paper/2110.12489/) (2021)
- [Demystifying and Extracting Fault-indicating Information from Logs for Failure Diagnosis](https://mlsanity.com/paper/2409.13561/) (2024)
- [Can LLMs Write CI? A Study on Automatic Generation of GitHub Actions Configurations](https://mlsanity.com/paper/2507.17165/) (2025)
- [Logging Practices with Mobile Analytics: An Empirical Study on Firebase](https://mlsanity.com/paper/2104.02513/) (2021)
- [CI/CD Configuration Practices in Open-Source Android Apps: An Empirical Study](https://mlsanity.com/paper/2411.06077/) (2024)
- [Understanding Abandonment and Slowdown Dynamics in the Maven Ecosystem](https://mlsanity.com/paper/2502.00615/) (2025)
- [An Empirical Study of Complexity, Heterogeneity, and Compliance of GitHub Actions Workflows](https://mlsanity.com/paper/2507.18062/) (2025)
- [Task-Aware Reduction for Scalable LLM-Database Systems](https://mlsanity.com/paper/2510.11813/) (2025)

## Built on by (most cited first, 1 of 1)

- [Can LLMs Really Recover Microservice Failures? A Recovery-Aware Evaluation of Diagnosis-to-Action Reasoning](https://mlsanity.com/paper/2607.04623/) (2026)

## Abstract (arXiv)

Logs are essential for understanding Continuous Integration (CI) behavior, particularly for diagnosing build failures and performance regressions. Yet their growing volume and verbosity make both manual inspection and automated analysis increasingly costly, time-consuming, and environmentally costly. While prior work has explored log compression, anomaly detection, and LLM-based log analysis, most efforts target structured system logs rather than the unstructured, noisy, and verbose logs typical of CI workflows. We present LogSieve, a lightweight, RCA-aware and semantics-preserving log reduction technique that filters low-information lines while retaining content relevant to downstream reasoning. Evaluated on CI logs from 20 open-source Android projects using GitHub Actions, LogSieve achieves an average 42% reduction in lines and 40% reduction in tokens with minimal semantic loss. This pre-inference reduction lowers computational cost and can proportionally reduce energy use (and associated emissions) by decreasing the volume of data processed during LLM inference. Compared with structure-first baselines (LogZip and random-line removal), LogSieve preserves much higher semantic and categorical fidelity (Cosine = 0.93, GPTScore = 0.93, 80% exact-match accuracy). Embedding-based classifiers automate relevance detection with near-human accuracy (97%), enabling scalable and sustainable integration of semantics-aware filtering into CI workflows. LogSieve thus bridges log management and LLM reasoning, offering a practical path toward greener and more interpretable CI automation.