# Towards Automatically Pruning Logging Code with Coding Agents: How Far Are We?

arXiv: https://arxiv.org/abs/2610.04716 · HTML: https://mlsanity.com/paper/2610.04716/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 69 references that are in the map.
- First posted on arXiv 3 Oct 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

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

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories](https://mlsanity.com/paper/2506.18824/) (2025)
- [TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use](https://mlsanity.com/paper/2510.04550/) (2025)
- [Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute](https://mlsanity.com/paper/2503.23803/) (2025)
- [Sampling Projects in GitHub for MSR Studies](https://mlsanity.com/paper/2103.04682/) (2021)
- [What Makes a Good Commit Message?](https://mlsanity.com/paper/2202.02974/) (2022)
- [Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios](https://mlsanity.com/paper/2410.12468/) (2024)
- [Using Deep Learning to Generate Complete Log Statements](https://mlsanity.com/paper/2201.04837/) (2022)
- [SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios](https://mlsanity.com/paper/2509.22097/) (2025)
- [Go Static: Contextualized Logging Statement Generation](https://mlsanity.com/paper/2402.12958/) (2024)
- [Studying Duplicate Logging Statements and Their Relationships with Code Clones](https://mlsanity.com/paper/2106.00339/) (2021)
- [FastLog: An End-to-End Method to Efficiently Generate and Insert Logging Statements](https://mlsanity.com/paper/2311.02862/) (2023)
- [LogUpdater: Automated Detection and Repair of Specific Defects in Logging Statements](https://mlsanity.com/paper/2408.03101/) (2024)
- [Do AI Coding Agents Log Like Humans? An Empirical Study](https://mlsanity.com/paper/2604.09409/) (2026)
- [Defects4Log: Benchmarking LLMs for Logging Code Defect Detection and Reasoning](https://mlsanity.com/paper/2508.11305/) (2025)
- [Towards Secure Logging: Characterizing and Benchmarking Logging Code Security Issues with LLMs](https://mlsanity.com/paper/2604.20211/) (2026)
- [AutoLogger: A Multi-Agent Framework for the End-to-End Automated Logging](https://mlsanity.com/paper/2511.18528/) (2025)
- [GitHub Template Repositories: Served Domains, Maintenance, and Practitioner Guidelines](https://mlsanity.com/paper/2606.14616/) (2026)
- [AgentExecutor: Partial Code Execution via Agentic Context Generation](https://mlsanity.com/paper/2608.05959/) (2026)

## Abstract (arXiv)

Logging code supports debugging, monitoring, and software maintenance, but excessive logging can add noise, impose runtime overhead, and obscure diagnostic information. While prior research has extensively studied logging code generation and modification, logging removal remains comparatively underexplored. In this paper, we study developer logging removal practices and explore the use of coding agents for this task. We extract and manually validate logging removal cases from Python and Java repositories and derive 10 removal patterns and 11 removal reasons that characterize how and why logging code was removed in real-world software changes. We further construct LogRem, a dataset of 387 real-world cases covering direct logging statement removal, logging infrastructure removal, and logging replacement. We evaluate four coding agents with multiple model settings and compare their outputs with accepted real-world changes. Although 95.6% to 100.0% of outputs pass validity checks, only 11.1% to 19.6% remove the same logging code as the corresponding real-world change while preserving unrelated code. Agents differ through missed removals, extra removals, and unrelated code edits, with substantial variation across logging removal categories and trajectories. Execution cost varies widely, but higher cost does not consistently yield closer alignment. Commit messages and developer discussions provide the largest alignment gains, while taxonomy guidance consistently reduces runtime. Overall, our study establishes logging removal as a distinct software maintenance task and shows that reliable automation depends on accurately determining removal scope while preserving necessary code. To the best of our knowledge, this is the first study to examine logging code removal from this perspective.