FullStack-Agent

Overview

This model is introduced in the paper "FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation". In this paper, we introduce FullStack-Agent, a unified system that combines a multi-agent full-stack development framework equipped with efficient coding and debugging tools (FullStack-Dev), an iterative self-improvement method that improves the abilities of LLMs through repository augmentation and back-translation (FullStack-Learn), and a full-stack development benchmark that comprehensively evaluates frontend, backend, and database functionalities (FullStack-Bench).

method

Quick Start

Instructions for installation and running of the three components are in the following documents:

Models

Model Name Huggingface Link
FullStack-Learn-LM-30B-A3B 🤗 luzimu/FullStack-Learn-LM-30B-A3B

Dataset

Dataset Name Huggingface Link
FullStack-Bench 🤗 luzimu/FullStack-Bench

Experimental Results

Experimental results of FullStack-Dev on FullStack-Bench compared to popular baseline methods are shown below:

main_results

The result of using more templates is presented below:

more_templates

Using more templates result in better performance in most of the metrics, which might be due to the fact that with more templates to choose from, the agent can find the most appropriate and easy-to-work-with templates, thus making the development process smoother.

Experimental results of FullStack-Learn tested on with FullStack-Dev on FullStack-Bench are as follows:

experiments

Downloads last month
4
Safetensors
Model size
31B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for luzimu/FullStack-Learn-LM-30B-A3B

Finetuned
(36)
this model
Quantizations
1 model

Paper for luzimu/FullStack-Learn-LM-30B-A3B