# Agentic Agile-V: From Vibe Coding to Verified Engineering in Software and Hardware Development arXiv: https://arxiv.org/abs/2605.20456 ยท HTML: https://mlsanity.com/paper/2605.20456/ ## Key facts - Cited by 2 papers in the map (data through 14 Oct 2026). - Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. - Builds on 27 of its 46 references that are in the map. - First posted on arXiv 19 May 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, 27 of 27) - [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024) - [A Survey on Code Generation with LLM-based Agents](https://mlsanity.com/paper/2508.00083/) (2025) - [Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity](https://mlsanity.com/paper/2507.09089/) (2025) - [SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?](https://mlsanity.com/paper/2603.15401/) (2026) - [On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub](https://mlsanity.com/paper/2509.14745/) (2025) - [The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents](https://mlsanity.com/paper/2511.03690/) (2025) - [A Survey of Research in Large Language Models for Electronic Design Automation](https://mlsanity.com/paper/2501.09655/) (2025) - [SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale](https://mlsanity.com/paper/2602.23866/) (2026) - [GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging](https://mlsanity.com/paper/2508.18993/) (2025) - [A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models](https://mlsanity.com/paper/2410.07265/) (2024) - [How much does AI impact development speed? An enterprise-based randomized controlled trial](https://mlsanity.com/paper/2410.12944/) (2024) - [Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?](https://mlsanity.com/paper/2602.11988/) (2026) - [RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving](https://mlsanity.com/paper/2505.21577/) (2025) - [On the Impact of AGENTS.md Files on the Efficiency of AI Coding Agents](https://mlsanity.com/paper/2601.20404/) (2026) - [AIDev: Studying AI Coding Agents on GitHub](https://mlsanity.com/paper/2602.09185/) (2026) - [RealBench: Benchmarking Verilog Generation Models with Real-World IP Designs](https://mlsanity.com/paper/2507.16200/) (2025) - [Harness Engineering for Agentic AI Coding Tools: An Exploratory Study](https://mlsanity.com/paper/2602.14690/) (2026) - [Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey](https://mlsanity.com/paper/2601.11655/) (2026) - [Measuring the Permission Gate: A Stress-Test Evaluation of Claude Code's Auto Mode](https://mlsanity.com/paper/2604.04978/) (2026) - [FIXME: Towards End-to-End Benchmarking of LLM-Aided Design Verification](https://mlsanity.com/paper/2507.04276/) (2025) - [Revolution or Hype? Seeking the Limits of Large Models in Hardware Design](https://mlsanity.com/paper/2509.04905/) (2025) - [Agentic Software Issue Resolution with Large Language Models: A Survey](https://mlsanity.com/paper/2512.22256/) (2025) - [Rethinking Software Engineering for Agentic AI Systems](https://mlsanity.com/paper/2604.10599/) (2026) - [Comparing AI Coding Agents: A Task-Stratified Analysis of Pull Request Acceptance](https://mlsanity.com/paper/2602.08915/) (2026) - [Instruction Adherence in Coding Agent Configuration Files: A Factorial Study of Four File-Structure Variables](https://mlsanity.com/paper/2605.10039/) (2026) - [Agile V: A Compliance-Ready Framework for AI-Augmented Engineering -- From Concept to Audit-Ready Delivery](https://mlsanity.com/paper/2602.20684/) (2026) - [A meta-analysis of the effect of generative AI on productivity and learning in programming](https://mlsanity.com/paper/2605.04779/) (2026) ## Built on by (most cited first, 2 of 2) - [Proof-or-Stop: Don't Trust the Agent, Trust the Evidence -- Loop Engineering for Verifiable Evidence-Gated Lifecycle Control](https://mlsanity.com/paper/2607.14890/) (2026) - [From Agent Output to Authorized Transition](https://mlsanity.com/paper/2609.28216/) (2026) ## Abstract (arXiv) Agentic AI coding systems can inspect repositories, plan implementation steps, edit files, call tools, run tests, and submit pull requests. These capabilities make software and hardware development faster in some settings, but current evidence does not support the simple claim that autonomous code generation automatically improves engineering outcomes. Controlled studies report productivity gains in some enterprise tasks, slowdowns in mature open-source work, moderate but heterogeneous meta-analytic effects, and persistent failures in repository setup, dependency handling, permission gating, and hardware verification. This paper argues that the central problem is no longer prompt engineering; it is engineering process control. It synthesizes evidence from agentic software engineering, GitHub-scale adoption studies, repository-level agent configuration, productivity trials, issue-resolution benchmarks, and hardware/RTL verification research. It proposes Agentic Agile-V, a process framework that uses Agile-V as the lifecycle backbone and a task-level SCOPE-V loop - Specify, Constrain, Orchestrate, Prove, Evolve, and Verify - to convert conversational intent into structured engineering artifacts and acceptance evidence. The paper contributes: (i) a taxonomy of minimum input artifacts for agentic software, firmware, and hardware work; (ii) a conversation-to-contract gate that separates exploratory dialogue from implementation; (iii) risk-adaptive feature, bug-fix, testing, and hardware workflows; and (iv) an evidence-bundle acceptance model for agent-generated artifacts. The paper concludes that agentic AI does not eliminate engineering discipline; it increases the value of requirements, constraints, traceability, independent verification, and human approval.