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

TL;DR

LogSieve is a lightweight, semantics-preserving log reduction technique for CI logs that significantly reduces data volume, lowers computational costs, and enhances sustainability while maintaining high relevance for downstream analysis.

Contribution

We introduce LogSieve, a novel log reduction method tailored for CI logs that preserves semantic content and improves efficiency compared to existing approaches.

Findings

Achieves 42% line reduction and 40% token reduction with minimal semantic loss.

Preserves high semantic fidelity with cosine similarity of 0.93.

Automates relevance detection with 97% accuracy.

Abstract

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.