arXiv AI
Aug 21
Escaping the Quicksand: A Call to Arms
arXiv:2608. 19674v1 Announce Type: cross Abstract: Computing has been an astonishing success - but the accumulated technical debt exposes us all to huge costs in business and societal risk.
Jas: AI-Paired Engineering as a Revival of N-Version Programming
arXiv:2606. 07828v1 Announce Type: cross Abstract: I report a case study in AI-paired software engineering: five working ports of a vector illustration application across Rust, Swift, OCaml, Python, and browser-based platforms, built by a single developer in approximately 120 evening hours.
Related stories
arXiv AI
Aug 12
Persistent Recursive Worlds Enable Autonomous Software Evolution
arXiv:2608. 10450v1 Announce Type: cross Abstract: Complex software systems develop over timescales that exceed the lifespan of any individual coding agent.
arXiv AI
Sep 7
Beyond Code Generation: Reliability, Verification, and Cost Economics in the Agentic Software Development Lifecycle
The paper examines how AI coding agents are evolving beyond simple autocomplete to perform complex tasks such as repository inspection, multi-file editing, tool execution, test writing, pull request creation, and long-duration work with minimal supervision. It highlights that while these agents boost coding activity, significant bottlenecks remain in review, integration, testing, security, deployment, and production operations, and that the economics of software development are shifting toward variable token, tool, sandbox, CI, and rework costs. The authors synthesize recent research and industry data to propose four engineering concepts—Agentic SDLC Throughput Paradox, Production-Qualified Change, Verification Tax, and an Agentic SDLC Control Plane—to guide the allocation of autonomy within cost, reliability, and human-attention constraints, ultimately reframing the research focus to production-qualified value per dollar, reviewer-hour, and operational risk.
arXiv AI
Aug 24
SDAD: Spec-Driven Agentic Development for the AI-Native SDLC
The paper introduces Spec-Driven Agentic Development (SDAD), a framework that leverages large language models to ingest extensive functional requirement documents and repository context in a single workflow, turning specification quality into the engine for autonomous software delivery. SDAD blends disciplined upfront formalisation with rapid implementation, encompassing intent capture, machine‑readable specifications, agentic synthesis, and multi‑agent verification with human sign‑off. It positions AI‑code as a fourth production paradigm, compares it to traditional Waterfall and Agile approaches, and extends the model to team role evolution, quantitative governance metrics, and a staged migration blueprint for practical adoption.
arXiv AI
Aug 10
Characterizing the Quality Profile of AI-Generated C++ in Production
arXiv:2608. 06640v1 Announce Type: cross Abstract: The widespread integration of AI coding assistants offers undeniable boosts to engineering velocity.
arXiv AI
Jun 30
MirrorCode: AI can rebuild entire programs from behavior alone
arXiv:2606. 30182v1 Announce Type: new Abstract: AI models are rapidly improving at autonomous coding, as shown by benchmark progress and one-off demonstrations such as AI implementing a C compiler.
arXiv AI
Sep 23
What is the Difference Between Me and You? Benchmarking the Quality Gap Between Human-Written and AI-Generated Code
arXiv:2609.12708v2 Announce Type: replace-cross Abstract: AI coding assistants are becoming co-authors of production software, yet their evaluation centers on functional correctness, leaving open whe...
arXiv AI
Sep 1
The reach of a verification tool decides its value: A controlled study of verification surface, artifact quality, and cost in AI coding agents
arXiv:2608.28795v1 Announce Type: cross Abstract: Modern artificial-intelligence coding agents can be equipped with tools for checking their own work e.g. a linter, a boot probe, a shell, a screensho...
arXiv AI
Sep 23
CraftBench-UE: Deterministic Evaluation for Coding Agents in Unreal Engine
arXiv:2609.23142v1 Announce Type: new Abstract: Building gameplay features in a game engine requires more than code, as code that compiles and runs does not necessarily implement the requested gamepl...
arXiv AI
Sep 17
A Study of the Reliability of Agentic AI-Generated Programs
The paper investigates the reliability of software produced by agentic AI by comparing AI-generated versions of ten well-known Linux utilities to their human-written counterparts. Using fuzz testing (both black-box and coverage-guided AFL++), the authors find that AI-generated code is often as reliable or more reliable than the latest human versions, with fewer memory errors but a higher incidence of hangs. The study emphasizes that robust AI-generated software requires careful prompting, skilled human oversight, and that the AI workflow can serve as a cost-effective specification for sustainable code.
arXiv AI
Jun 26
The Spec Growth Engine: Spec-Anchored, Code-Coupled, Drift-Enforced Architecture for AI-Assisted Software Development
arXiv:2606. 27045v1 Announce Type: cross Abstract: AI coding agents dramatically accelerate implementation speed but introduce two structural failure modes that existing spec-driven approaches do not fully solve: (1) context explosion -- the agent must reason over an entire repository at once, degrading output quality as the context window fills; and (2) silent spec-code drift -- code evolves, the specification does not, and the divergence becomes invisible until it is costly to repair.
arXiv AI
Aug 14
IACDM: Interactive Adversarial Convergence Development Methodology -- A Structured Framework for AI-Assisted Software Development
arXiv:2604. 16399v3 Announce Type: replace-cross Abstract: Adoption of AI-assisted development in 2025 exposed a tool-agnostic failure pattern: experienced developers using frontier models were measurably slower while believing they were faster, and 10.