Cheap Code, Costly Judgment: A Case Study on Governable Agentic Software Engineering

• URL: http://arxiv.org/abs/2607.01087v2
• Date: Sat, 04 Jul 2026 20:01:57 GMT
• Title: Cheap Code, Costly Judgment: A Case Study on Governable Agentic Software Engineering
• Abstract summary: 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.
• Score: 8.368707686524482
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative AI is shifting software engineering from a practice organized around scarce implementation effort toward one organized around abundant, low-cost code production. This shift changes the central engineering problem: not whether AI can generate useful code, but how engineers organize architectures, tools, evidence, and feedback loops so that AI-mediated development remains inspectable, correctable, and maintainable. We study this problem through a first-person case study: a 12-week development effort in which a single expert software engineer used frontier AI coding agents to build a document accessibility remediation system. The empirical record comprises 88 contemporaneous field notes, 420 KLOC of production code, and 1.16 MLOC of tests, lints, supporting documentation, and agent tooling. From this record, we develop a candidate middle-range theory of governance conversion, expressed as a process model explaining how high-velocity agentic implementation becomes governable. The model explains how agentic implementation velocity surfaces recurring structural failure classes, and how engineering judgment sustains velocity by converting those failures into durable governance mechanisms. In contrast to existing governance models that derive controls from known obligations, governance conversion explains how controls are discovered from failures that become visible only during agentic work. We use our model to make testable predictions and to describe implications for software engineering research and practice.

Related papers

• On Automated and Explainable Provenance of AI-Generated Code [56.818202904805446]
  We argue that the next generation of CodeGenAI tools must be built on a foundation of explainable provenance.<n>We describe a research program combining large-scale empirical studies with post-hoc causal and interpretability techniques.
  arXiv  Detail & Related papers  (2026-08-03T14:50:31Z)
• From Determinism to Delegation: AI-Native Software Engineering and the Evolution of the Agentic Engineer [0.0]
  Software engineering is experiencing its most significant transformation since the emergence of high-level programming languages.<n>This paper argues that AI-Native Software Engineering is a paradigm shift rather than a mere tooling advance.<n>We define core mechanisms of autonomous agents, including reasoning-acting loops, context engineering, tool use, memory, behavioral drift, and compositional error.
  arXiv  Detail & Related papers  (2026-06-27T07:43:43Z)
• AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systems [82.01232437066487]
  AgentX is a production-deployed multi-agent system that restructures this production function.<n>It autonomously generates, implements, evaluates, and learns from recommendation experiments.<n>AgentX orchestrates four tightly coupled stages in a closed loop.
  arXiv  Detail & Related papers  (2026-06-25T10:42:28Z)
• 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)
• AI for Auto-Research: Roadmap & User Guide [107.0834449839233]
  We present an end-to-end analysis of AI across the complete research lifecycle.<n>We identify a sharp, stage-dependent boundary between reliable assistance and unreliable autonomy.<n>We show that greater automation can obscure rather than eliminate failure modes.
  arXiv  Detail & Related papers  (2026-05-18T17:08:26Z)
• Bridging the Gap on AI-Assisted Scientific Software Development Through Transparency and Traceability [4.466942018046944]
  Researchers are already using large language models to write code, generate test cases, and draft documentation.<n>This ad hoc, ungoverned use of AI represents a systemic risk to scientific software quality.<n>This paper proposes guidance for AI-assisted code development in the context of strict software quality assurance.
  arXiv  Detail & Related papers  (2026-05-17T22:08:52Z)
• AI-Generated Smells: An Analysis of Code and Architecture in LLM and Agent-Driven Development [1.980498913496519]
  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.
  arXiv  Detail & Related papers  (2026-05-04T15:41:13Z)
• Shift-Up: A Framework for Software Engineering Guardrails in AI-native Software Development -- Initial Findings [1.1523102135577732]
  Generative AI (GenAI) is reshaping software engineering by shifting development from manual coding toward agent-driven implementation.<n>This paper proposes Shift-Up, a framework that reinterprets established software engineering practices, like executable requirements (BDD), architectural modeling (C4), and architecture decision records (ADRs) as structural guardrails for GenAI-native development.
  arXiv  Detail & Related papers  (2026-04-22T10:55:57Z)
• The Semi-Executable Stack: Agentic Software Engineering and the Expanding Scope of SE [3.6320170149653985]
  AI-based systems are increasingly discussed as a possible threat to software engineering.<n>This paper argues for a different reading.<n>It is that the thing being engineered expands beyond executable code to semi-executable artifacts.
  arXiv  Detail & Related papers  (2026-04-16T18:36:02Z)
• Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows [60.04362496037186]
  We present the first controlled study of developer interactions with coding agents.<n>We evaluate two leading copilot and agentic coding assistants.<n>Our results show agents can assist developers in ways that surpass copilots.
  arXiv  Detail & Related papers  (2025-07-10T20:12:54Z)
• Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions [54.55334589363247]
  We study whether conveying information about uncertainty enables programmers to more quickly and accurately produce code. We find that highlighting tokens with the highest predicted likelihood of being edited leads to faster task completion and more targeted edits.
  arXiv  Detail & Related papers  (2023-02-14T18:43:34Z)

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.