Is Agent Code Less Maintainable Than Human Code?

• URL: http://arxiv.org/abs/2606.21804v1
• Date: Fri, 19 Jun 2026 23:56:14 GMT
• Title: Is Agent Code Less Maintainable Than Human Code?
• Abstract summary: We investigate how agent code compares to human code in maintenance settings.<n>We find that agents are less effective at resolving tasks when building on agent code compared to human code.
• Score: 17.226150835020146
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Maintainability is a core dimension of software engineering, shaping how code is written, reviewed, and developed over time. While coding agents have demonstrated strong performance on single-issue tasks, it remains unclear how maintainable their code is when future agents build on top of it, potentially leading to compounding downstream effects. We investigate how agent code compares to human code in these maintenance settings, presenting CodeThread, a framework to construct controlled experiments from repository-level coding benchmarks. Applying CodeThread to four frontier coding agents and four benchmarks, we find that agents are less effective at resolving tasks when building on agent code compared to human code, with task resolve rate drops of up to 13.1%. Regression analysis reveals that many traditional software engineering maintainability metrics do not explain this difference. Instead, the clearest signals are subtler behavioral differences in agent code, such as changes to input validation and error handling, along with differences in downstream code size and task difficulty. These findings highlight the need to evaluate these systems not only by immediate task resolution but also by code maintainability, and point to potential sources of downstream errors introduced by agent code.

Related papers

• TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory Minimization [57.14479960309637]
  Coding agents are increasingly used to accelerate code generation in many downstream tasks.<n>Despite their value, agent-generated code tends to be larger and more verbose than the corresponding human-written implementation.<n>We show that the cause lies in the agent's own search process.
  arXiv  Detail & Related papers  (2026-07-20T17:06:19Z)
• The End of Code Review: Coding Agents Supersede Human Inspection [7.017303286271101]
  We argue that coding agents have crossed a threshold of capability at which traditional human code review is no longer a necessary component of a software quality pipeline.<n>Our argument rests on two claims: every stated goal of code review can be served by agents at lower cost and higher throughput.
  arXiv  Detail & Related papers  (2026-06-11T10:43:48Z)
• SmellBench: Towards Fine-Grained Evaluation of Code Agents on Refactoring Tasks [34.43588103259487]
  SmellBench proactively injects code smells into clean code from real-world repositories.<n>It contains 294 cases spanning 7 popular smell types, 3 difficulty levels, 2 instruction settings across 7 real-world repositories.<n>Experiments show that the best combination - Qwenwen Code + Sonnet 4.5 - achieved only a 50.34 score of smell elimination.
  arXiv  Detail & Related papers  (2026-06-04T01:49:07Z)
• Does Code Cleanliness Affect Coding Agents? A Controlled Minimal-Pair Study [0.18907108368038217]
  We show that code cleanliness affects an agent's ability to navigate and modify it.<n>Our findings suggest that traditional maintainability principles remain highly relevant in the era of AI-driven development.
  arXiv  Detail & Related papers  (2026-05-19T16:06:26Z)
• Code as Agent Harness [107.31925305395957]
  In emerging agentic systems, code is no longer only a target output.<n>Code increasingly serves as an operational substrate for agent reasoning, acting, environment modeling, and execution-based verification.<n>This survey provides a unified roadmap toward executable, verifiable, and stateful AI agent systems.
  arXiv  Detail & Related papers  (2026-05-18T17:59:03Z)
• SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks [55.76734816061826]
  We introduce SlopCodeBench, a language-agnostic benchmark comprising 20 problems and 93 checkpoints.<n>We track two trajectory-level quality signals: verbosity, the fraction of redundant or duplicated code, and structural erosion.<n>No agent solves any problem end-to-end across 11 models; the highest checkpoint solve rate is 17.2%.
  arXiv  Detail & Related papers  (2026-03-25T19:26:44Z)
• RedCode: Risky Code Execution and Generation Benchmark for Code Agents [50.81206098588923]
  RedCode is a benchmark for risky code execution and generation. RedCode-Exec provides challenging prompts that could lead to risky code execution. RedCode-Gen provides 160 prompts with function signatures and docstrings as input to assess whether code agents will follow instructions.
  arXiv  Detail & Related papers  (2024-11-12T13:30:06Z)
• Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion? [60.84912551069379]
  We present the Code-Development Benchmark (Codev-Bench), a fine-grained, real-world, repository-level, and developer-centric evaluation framework. Codev-Agent is an agent-based system that automates repository crawling, constructs execution environments, extracts dynamic calling chains from existing unit tests, and generates new test samples to avoid data leakage.
  arXiv  Detail & Related papers  (2024-10-02T09:11:10Z)
• CodeAgent: Autonomous Communicative Agents for Code Review [12.163258651539236]
  This work introduces tool, a novel multi-agent Large Language Model (LLM) system for code review automation. CodeAgent incorporates a supervisory agent, QA-Checker, to ensure that all the agents' contributions address the initial review question. Results demonstrate CodeAgent's effectiveness, contributing to a new state-of-the-art in code review automation.
  arXiv  Detail & Related papers  (2024-02-03T14:43:14Z)
• CONCORD: Clone-aware Contrastive Learning for Source Code [64.51161487524436]
  Self-supervised pre-training has gained traction for learning generic code representations valuable for many downstream SE tasks. We argue that it is also essential to factor in how developers code day-to-day for general-purpose representation learning. In particular, we propose CONCORD, a self-supervised, contrastive learning strategy to place benign clones closer in the representation space while moving deviants further apart.
  arXiv  Detail & Related papers  (2023-06-05T20:39:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.