From Runnable to Shippable: Multi-Agent Test-Driven Development for Generating Full-Stack Web Applications from Requirements

• URL: http://arxiv.org/abs/2605.17242v1
• Date: Sun, 17 May 2026 03:48:41 GMT
• Title: From Runnable to Shippable: Multi-Agent Test-Driven Development for Generating Full-Stack Web Applications from Requirements
• Abstract summary: Test-driven development (TDDev) is a framework that automates this closed loop through three stages.<n>We conduct the first controlled empirical study of Test-driven development strategies for web application generation.<n> TDDev reduces manual developer intervention to zero, shifting the workload from continuous prompt engineering to autonomous, feedback-driven refinement.
• Score: 34.560333810255464
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Coding agents can generate web applications from natural-language descriptions, yet a recent benchmark study shows that generated applications fail to meet functional requirements in over 70% of cases. The core difficulty is that web correctness cannot be assessed from source files or terminal output: the application must be deployed, exercised through simulated browser interactions, and failures must be translated into actionable repair signals -- steps that current agents cannot perform without human mediation. We present TDDev, a framework that automates this closed loop through three stages: (1) converting high-level requirements into structured acceptance tests before any code is written, (2) deploying the application and validating it through browser-based interaction simulation, and (3) translating browser-observed failures into structured repair reports for the coding agent. Enabled by TDDev, we conduct the first controlled empirical study of Test-driven development (TDD) strategies for web application generation, comparing four development protocols across two coding agents, two backbone models, and two benchmarks. TDD infrastructure consistently improves generation quality by 34--48 percentage points over a no-TDD baseline. The central finding is that the optimal protocol depends on the model's generation style: models that build applications holistically benefit most from agentic enforcement, while models that extend code conservatively benefit from incremental enforcement. Mismatching protocol to generation style eliminates the TDD benefit entirely while multiplying token cost up to 25-fold. A user study confirms that TDDev reduces manual developer intervention to zero, shifting the workload from continuous prompt engineering to autonomous, feedback-driven refinement.

Related papers

• TDD-Agent: Test-Driven Reasoning for Code Generation [12.09256800328452]
  Existing approaches use generated tests as static post-hoc validators.<n>We introduce TDD-Agent, which operationalizes the test-driven development paradigm for code generation.
  arXiv  Detail & Related papers  (2026-08-17T15:52:04Z)
• TraceDev: A Traceability-Driven Multi-agent Framework for Requirement-to-Code Development [17.91255349277154]
  TraceDev is a multi-agent framework for automated software development grounded in use cases that contain multiple functional points and complex semantics.<n>We evaluate TraceDev on two widely used datasets (including 125 use cases) compared with two state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-07-21T09:14:59Z)
• GTA: Generating Long-Horizon Tasks for Web Agents at Scale [82.43869456830664]
  We introduce a scalable framework, GTA, that integrates crawling, retrieval-based seeding, in-context generation, and automated quality control.<n>We instantiate the pipeline on over 50 websites covering e-commerce, government, forums, and news, with multilingual and multi-hop coverage.<n>Our contributions are three-fold: (i) formalizing multi-hop web-agent task generation, (ii) proposing an efficient and validated pipeline for automatic data creation, and (iii) releasing a dynamic benchmark with reproducible evaluation.
  arXiv  Detail & Related papers  (2026-05-28T01:05:50Z)
• ChipMATE: Multi-Agent Training via Reinforcement Learning for Enhanced RTL Generation [55.947962672433675]
  ChipMATE is the first self-trained multi-agent framework for RTL generation.<n>Inspired by industrial practice, ChipMATE pairs a Verilog agent with a Python reference-model agent that mutually verify each other's outputs.<n>ChipMATE achieves 75.0% and 80.1% pass@1 on VerilogEval V2 with 4B and 9B base models.
  arXiv  Detail & Related papers  (2026-05-13T01:04:21Z)
• GTA-2: Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflows [90.35728421223673]
  GTA-2 is a hierarchical benchmark for General Tool Agents (GTA)<n>Built on real-world authenticity, it leverages real user queries, deployed tools, and multimodal contexts.<n>Experiments reveal a pronounced capability cliff: while frontier models already struggle on atomic tasks, top models achieving only 14.39% success.
  arXiv  Detail & Related papers  (2026-04-17T05:36:00Z)
• Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback [51.22403664895878]
  Agent2World is a tool-augmented multi-agent framework that achieves strong inference-time world-model generation.<n>It also serves as a data engine for supervised fine-tuning, by grounding generation in multi-agent feedback.
  arXiv  Detail & Related papers  (2025-12-26T18:54:14Z)
• Automatically Generating Web Applications from Requirements Via Multi-Agent Test-Driven Development [34.560333810255464]
  We introduce TDDev, the first test-driven development framework for end-to-end full-stack web application generation.<n>Given a natural language description or design image, TDDev automatically derives executable test cases, generates front-end and back-end code, and simulates user interactions.<n>Our framework addresses key challenges in full-stack automation, including underspecified user requirements, complex interdependencies among multiple files, and the need for both functional correctness and visual fidelity.
  arXiv  Detail & Related papers  (2025-09-29T16:18:19Z)
• TENET: Leveraging Tests Beyond Validation for Code Generation [15.74797688806215]
  Test-Driven Development (TDD) is a widely adopted software engineering practice that requires developers to create and execute tests alongside code implementation.<n>This paper introduces TENET, an agent for generating functions in complex real-world repositories under the TDD setting.<n> TENET achieves 69.08% and 81.77% Pass@1 on RepoCod and RepoEval benchmarks, outperforming the best agentic baselines by 9.49 and 2.17 percentage points, respectively.
  arXiv  Detail & Related papers  (2025-09-29T00:53:16Z)
• Reinforcement Learning for Machine Learning Engineering Agents [52.03168614623642]
  We show that agents backed by weaker models that improve via reinforcement learning can outperform agents backed by much larger, but static models.<n>We propose duration- aware gradient updates in a distributed asynchronous RL framework to amplify high-cost but high-reward actions.<n>We also propose environment instrumentation to offer partial credit, distinguishing almost-correct programs from those that fail early.
  arXiv  Detail & Related papers  (2025-09-01T18:04:10Z)
• SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents [50.82665351100067]
  FlowGen is a code generation framework that emulates software process models based on multiple Large Language Model (LLM) agents. We evaluate FlowGenScrum on four benchmarks: HumanEval, HumanEval-ET, MBPP, and MBPP-ET.
  arXiv  Detail & Related papers  (2024-03-23T14:04:48Z)

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.