Generating Move Smart Contracts based on Concepts
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929634996649984 |
|---|---|
| author | Karanjai, Rabimba Blackshear, Sam Xu, Lei Shi, Weidong |
| author_facet | Karanjai, Rabimba Blackshear, Sam Xu, Lei Shi, Weidong |
| contents | The growing adoption of formal verification for smart contracts has spurred the development of new verifiable languages like Move. However, the limited availability of training data for these languages hinders effective code generation by large language models (LLMs). This paper presents ConMover, a novel framework that enhances LLM-based code generation for Move by leveraging a knowledge graph of Move concepts and a small set of verified code examples. ConMover integrates concept retrieval, planning, coding, and debugging agents in an iterative process to refine generated code. Evaluations with various open-source LLMs demonstrate substantial accuracy improvements over baseline models. These results underscore ConMover's potential to address low-resource code generation challenges, bridging the gap between natural language descriptions and reliable smart contract development. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_12513 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generating Move Smart Contracts based on Concepts Karanjai, Rabimba Blackshear, Sam Xu, Lei Shi, Weidong Software Engineering The growing adoption of formal verification for smart contracts has spurred the development of new verifiable languages like Move. However, the limited availability of training data for these languages hinders effective code generation by large language models (LLMs). This paper presents ConMover, a novel framework that enhances LLM-based code generation for Move by leveraging a knowledge graph of Move concepts and a small set of verified code examples. ConMover integrates concept retrieval, planning, coding, and debugging agents in an iterative process to refine generated code. Evaluations with various open-source LLMs demonstrate substantial accuracy improvements over baseline models. These results underscore ConMover's potential to address low-resource code generation challenges, bridging the gap between natural language descriptions and reliable smart contract development. |
| title | Generating Move Smart Contracts based on Concepts |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2412.12513 |