AI-Generated Smells: An Analysis of Code and Architecture in LLM and Agent-Driven Development

• URL: http://arxiv.org/abs/2605.02741v1
• Date: Mon, 04 May 2026 15:41:13 GMT
• Title: AI-Generated Smells: An Analysis of Code and Architecture in LLM and Agent-Driven Development
• Abstract summary: This paper presents a systematic audit of technical debt in AI-generated software.<n>We show that AI does not eliminate flaws but rather introduces a distinct machine signature of defects.<n>We conclude that future progress depends on equipping agents with explicit architectural foresight to ensure the software they build is not just functional, but also maintainable.
• Score: 1.980498913496519
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The promise of Large Language Models in automated software engineering is often measured by functional correctness, overlooking the critical issue of long term maintainability. This paper presents a systematic audit of technical debt in AI-generated software, revealing that AI does not eliminate flaws but rather introduces a distinct machine signature of defects. Our multi-scale analysis, spanning single-file algorithmic tasks and complex, agent generated systems, identifies a fundamental Reasoning-Complexity Trade-off: as models become more capable, they generate increasingly bloated and coupled code. This architectural decay is so pronounced that we establish a Volume-Quality Inverse Law, where code volume is a near perfect predictor of structural degradation. Crucially, we demonstrate that neither functional correctness nor detailed prompting mitigates this decay. These findings challenge the current paradigm of prompt-driven generation, reframing the central problem of AI-based software engineering from one of code generation to one of architectural complexity management. We conclude that future progress depends on equipping agents with explicit architectural foresight to ensure the software they build is not just functional, but also maintainable.

Related papers

• Continuous Autonomous Refactoring: A Research Roadmap for AI-Driven Code Quality Maintenance [3.0540716731676625]
  We envision LLM-based pipelines as a continuous component of software maintenance rather than a tool invoked only for occasional manual tasks.<n>Under this vision, AI agents continuously monitor, evaluate, and improves against explicit and evolving notions of software quality.
  arXiv  Detail & Related papers  (2026-09-01T13:35:29Z)
• The Specification Paradox: Rethinking Requirements Engineering in the Age of AI [0.0]
  This article discusses the transition from a code-centered paradigm to Specification-Driven Development.<n>We argue that artificial intelligence reduces some of the effort associated with writing source code, but it does not eliminate the complexity of developing professional software systems.<n>We conclude that the future of Software Engineering will depend not only on machines' ability to generate code, but also on humans' ability to correctly specify, evaluate, and evolve what is intended to be built.
  arXiv  Detail & Related papers  (2026-08-17T14:19:14Z)
• Cheap Code, Costly Judgment: A Case Study on Governable Agentic Software Engineering [8.368707686524482]
  We study how engineers organize architectures, tools, evidence, and feedback loops so that AI-mediated development remains inspectable, correctable, and maintainable.<n>We develop a theory of governance conversion, expressed as a process model explaining how high-velocity agentic implementation becomes governable.
  arXiv  Detail & Related papers  (2026-07-01T15:44:15Z)
• Cognitive Atrophy and Systemic Collapse in AI-Dependent Software Engineering [0.0]
  This paper introduces "Epistemological Debt," the hidden carrying cost incurred when engineers substitute logical derivation with passive AI verification.<n>This debt erodes the mental models essential for root-cause analysis, widening the gap between system complexity and human comprehension.<n>Using the 2026 Amazon outages as a case study, this research illustrates how "mechanized convergence" leads to systemic fragility.
  arXiv  Detail & Related papers  (2026-04-29T16:20:25Z)
• Towards Automated Ontology Generation from Unstructured Text: A Multi-Agent LLM Approach [1.029029220360574]
  Large language models (LLMs) show promise, but it remains unclear which architectural design choices drive generation quality.<n>We present a controlled experimental study using domain-specific insurance contracts to investigate these questions.<n>Results show that the multi-agent approach significantly improves structural quality and modestly enhances queryability.
  arXiv  Detail & Related papers  (2026-04-25T00:58:17Z)
• Dynamic analysis enhances issue resolution [53.50448142467294]
  DAIRA (Dynamic Analysis-enhanced Issue Resolution Agent) is an automated repair framework that embeds dynamic analysis into the agent's reasoning cycle.<n> Driven by a Test Tracing-Driven methodology, DAIRA utilizes lightweight monitors to extract critical runtime data.<n>When powered by Gemini 3 Flash Preview, DAIRA establishes a new state-of-the-art (SOTA) performance, achieving a 79.4% resolution rate on the SWE-bench Verified dataset.
  arXiv  Detail & Related papers  (2026-03-23T14:48:54Z)
• Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining [66.89012795621349]
  Large Language Models (LLMs) often struggle with the deep, long-horizon reasoning required for complex software engineering.<n>We propose a novel paradigm: understanding via reconstruction.<n>We introduce a framework that synthesizes latent agentic trajectories using a multi-agent simulation.
  arXiv  Detail & Related papers  (2026-03-11T09:23:20Z)
• Quality-Driven Agentic Reasoning for LLM-Assisted Software Design: Questions-of-Thoughts (QoT) as a Time-Series Self-QA Chain [0.0]
  We introduce Questions-of-Thoughts (QoT), a quality-driven inference-time scaffold that turns a user goal into an ordered sequence of engineering steps.<n>We evaluate QoT across three representative backend engineering domains: API Design, Data Communication, and File Systems.
  arXiv  Detail & Related papers  (2026-03-10T23:49:09Z)
• Architecture-Aware Multi-Design Generation for Repository-Level Feature Addition [53.50448142467294]
  RAIM is a multi-design and architecture-aware framework for repository-level feature addition.<n>It shifts away from linear patching by generating multiple diverse implementation designs.<n>Experiments on the NoCode-bench Verified dataset demonstrate that RAIM establishes a new state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-03-02T12:50:40Z)
• EmboCoach-Bench: Benchmarking AI Agents on Developing Embodied Robots [68.29056647487519]
  Embodied AI is fueled by high-fidelity simulation and large-scale data collection.<n>However, this scaling capability remains bottlenecked by a reliance on labor-intensive manual oversight.<n>We introduce textscEmboCoach-Bench, a benchmark evaluating the capacity of LLM agents to autonomously engineer embodied policies.
  arXiv  Detail & Related papers  (2026-01-29T11:33:49Z)
• Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey [59.3507264893654]
  Issue resolution is a complex Software Engineering task integral to real-world development.<n> benchmarks like SWE-bench revealed this task as profoundly difficult for large language models.<n>This paper presents a systematic survey of this emerging domain.
  arXiv  Detail & Related papers  (2026-01-15T18:55:03Z)
• Lost in Code Generation: Reimagining the Role of Software Models in AI-driven Software Engineering [1.3124479769761592]
  We argue that this shift motivates a reimagining of software models.<n>Rather than serving only as upfront blueprints, models can be recovered post-hoc from AI-generated code.<n>In this role, models serve as mediators between human intent, AI generation, and long-term system evolution.
  arXiv  Detail & Related papers  (2025-11-04T11:03:31Z)
• Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute [61.00662702026523]
  We propose a unified Test-Time Compute scaling framework that leverages increased inference-time instead of larger models.<n>Our framework incorporates two complementary strategies: internal TTC and external TTC.<n>We demonstrate our textbf32B model achieves a 46% issue resolution rate, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1.
  arXiv  Detail & Related papers  (2025-03-31T07:31:32Z)

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.