mlsanityData to 7 Oct 2026

FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation

arXiv 2602.03798 ↗First posted 3 Feb 2026cs.SE cs.CL cs.CVcited by 2

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

Assisting non-expert users to develop complex interactive websites has become a popular task for LLM-powered code agents. However, existing code agents tend to only generate frontend web pages, masking the lack of real full-stack data processing and storage with fancy visual effects. Notably, constructing production-level full-stack web applications is far more challenging than only generating frontend web pages, demanding careful control of data flow, comprehensive understanding of constantly updating packages and dependencies, and accurate localization of obscure bugs in the codebase. To address these difficulties, we introduce FullStack-Agent, a unified agent system for full-stack agentic coding that consists of three parts: (1) FullStack-Dev, a multi-agent framework with strong planning, code editing, codebase navigation, and bug localization abilities. (2) FullStack-Learn, an innovative data-scaling and self-improving method that back-translates crawled and synthesized website repositories to improve the backbone LLM of FullStack-Dev. (3) FullStack-Bench, a comprehensive benchmark that systematically tests the frontend, backend and database functionalities of the generated website. Our FullStack-Dev outperforms the previous state-of-the-art method by 8.7%, 38.2%, and 15.9% on the frontend, backend, and database test cases respectively. Additionally, FullStack-Learn raises the performance of a 30B model by 9.7%, 9.5%, and 2.8% on the three sets of test cases through self-improvement, demonstrating the effectiveness of our approach. The code is released at https://github.com/mnluzimu/FullStack-Agent.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 16 of its 27 references that are in the map. First posted on arXiv 3 Feb 2026.

Builds on

16 of 27 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Automatically Generating Web Applications from Requirements Via Multi-Agent Test-Driven Development29 Sep
  2. 2025Web-Bench: A LLM Code Benchmark Based on Web Standards and Frameworks12 May
  3. 2025WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch6 May
  4. 2025SEAlign: Alignment Training for Software Engineering Agent24 Mar
  5. 2024Training Software Engineering Agents and Verifiers with SWE-Gym30 Dec

Other references · 11

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2024Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineeringcited by 146
  4. 2024Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Datasetcited by 126
  5. 2024Interaction2Code: Benchmarking MLLM-based Interactive Webpage Code Generation from Interactive Prototypingcited by 50
  6. 2024WebCode2M: A Real-World Dataset for Code Generation from Webpage Designscited by 43
  7. 2025DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generationcited by 41
  8. 2025SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuningcited by 27
  9. 2025FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflowcited by 25
  10. 2024MRWeb: An Exploration of Generating Multi-Page Resource-Aware Web Code from UI Designscited by 23
  11. 2024IW-Bench: Evaluating Large Multimodal Models for Converting Image-to-Webcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generationcited by 2
  2. 2026MultiTalk: Scaling Full-Duplex Speech Models to Long, Multi-Party, Bilingual Conversationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization
  2. 2026SW-A2-Bench: Benchmarking Autonomous Software Agent Generation for Agentic Web
  3. 2025Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases
  4. 2026VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents
  5. 2024CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges
  6. 2025SEW: Self-Evolving Agentic Workflows for Automated Code Generation
  7. 2025WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning
  8. 2026From Runnable to Shippable: Multi-Agent Test-Driven Development for Generating Full-Stack Web Applications from Requirements