Add library_name and citation, fix quick start links
#1
by
nielsr
HF Staff
- opened
README.md
CHANGED
|
@@ -1,25 +1,28 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
| 3 |
language:
|
| 4 |
- en
|
|
|
|
| 5 |
metrics:
|
| 6 |
- accuracy
|
| 7 |
-
base_model:
|
| 8 |
-
- Qwen/Qwen3-Coder-30B-A3B-Instruct
|
| 9 |
pipeline_tag: text-generation
|
|
|
|
| 10 |
tags:
|
| 11 |
- code
|
| 12 |
- agent
|
| 13 |
---
|
| 14 |
|
| 15 |
-
|
| 16 |
# FullStack-Agent
|
| 17 |
|
| 18 |
### Overview
|
| 19 |
|
| 20 |
This model is introduced in the paper ["FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation"](https://arxiv.org/abs/2602.03798).
|
|
|
|
| 21 |
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](https://github.com/mnluzimu/FullStack-Dev)), an iterative self-improvement method that improves the abilities of LLMs through repository augmentation and back-translation ([FullStack-Learn](https://github.com/mnluzimu/FullStack-Learn)), and a full-stack development benchmark that comprehensively evaluates frontend, backend, and database functionalities ([FullStack-Bench](https://github.com/mnluzimu/FullStack-Bench)).
|
| 22 |
|
|
|
|
|
|
|
| 23 |

|
| 24 |
|
| 25 |
### Quick Start
|
|
@@ -30,7 +33,7 @@ Instructions for installation and running of the three components are in the fol
|
|
| 30 |
|
| 31 |
- [FullStack-Learn](https://github.com/mnluzimu/FullStack-Learn)
|
| 32 |
|
| 33 |
-
- [FullStack-
|
| 34 |
|
| 35 |
### Models
|
| 36 |
|
|
@@ -60,4 +63,20 @@ Using more templates result in better performance in most of the metrics, which
|
|
| 60 |
|
| 61 |
Experimental results of FullStack-Learn tested on with FullStack-Dev on FullStack-Bench are as follows:
|
| 62 |
|
| 63 |
-

|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model:
|
| 3 |
+
- Qwen/Qwen3-Coder-30B-A3B-Instruct
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
+
license: apache-2.0
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
|
|
|
|
|
|
| 9 |
pipeline_tag: text-generation
|
| 10 |
+
library_name: transformers
|
| 11 |
tags:
|
| 12 |
- code
|
| 13 |
- agent
|
| 14 |
---
|
| 15 |
|
|
|
|
| 16 |
# FullStack-Agent
|
| 17 |
|
| 18 |
### Overview
|
| 19 |
|
| 20 |
This model is introduced in the paper ["FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation"](https://arxiv.org/abs/2602.03798).
|
| 21 |
+
|
| 22 |
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](https://github.com/mnluzimu/FullStack-Dev)), an iterative self-improvement method that improves the abilities of LLMs through repository augmentation and back-translation ([FullStack-Learn](https://github.com/mnluzimu/FullStack-Learn)), and a full-stack development benchmark that comprehensively evaluates frontend, backend, and database functionalities ([FullStack-Bench](https://github.com/mnluzimu/FullStack-Bench)).
|
| 23 |
|
| 24 |
+
Official Repository: [mnluzimu/FullStack-Agent](https://github.com/mnluzimu/FullStack-Agent)
|
| 25 |
+
|
| 26 |

|
| 27 |
|
| 28 |
### Quick Start
|
|
|
|
| 33 |
|
| 34 |
- [FullStack-Learn](https://github.com/mnluzimu/FullStack-Learn)
|
| 35 |
|
| 36 |
+
- [FullStack-Bench](https://github.com/mnluzimu/FullStack-Bench)
|
| 37 |
|
| 38 |
### Models
|
| 39 |
|
|
|
|
| 63 |
|
| 64 |
Experimental results of FullStack-Learn tested on with FullStack-Dev on FullStack-Bench are as follows:
|
| 65 |
|
| 66 |
+

|
| 67 |
+
|
| 68 |
+
### Citation
|
| 69 |
+
|
| 70 |
+
If you find our project helpful, please cite:
|
| 71 |
+
|
| 72 |
+
```bibtex
|
| 73 |
+
@misc{lu2026fullstackagentenhancingagenticfullstack,
|
| 74 |
+
title={FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation},
|
| 75 |
+
author={Zimu Lu and Houxing Ren and Yunqiao Yang and Ke Wang and Zhuofan Zong and Mingjie Zhan and Hongsheng Li},
|
| 76 |
+
year={2026},
|
| 77 |
+
eprint={2602.03798},
|
| 78 |
+
archivePrefix={arXiv},
|
| 79 |
+
primaryClass={cs.SE},
|
| 80 |
+
url={https://arxiv.org/abs/2602.03798},
|
| 81 |
+
}
|
| 82 |
+
```
|