Add library_name and citation, fix quick start links

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +25 -6
README.md CHANGED
@@ -1,25 +1,28 @@
1
  ---
2
- license: apache-2.0
 
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
  ![method](assets/method.png)
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-Learn](https://github.com/mnluzimu/FullStack-Learn)
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
- ![experiments](assets/experiments.png)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
  ![method](assets/method.png)
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
+ ![experiments](assets/experiments.png)
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
+ ```