by nju-websoft · Agent Tool · ★ 111
PairCoder 🤖💻 This paper has been accepted by ASE 2024 and awarded the 🏆 ACM SIGSOFT Distinguished Paper Award. 📖Overview • 🧪Environment • 📂Dataset Setup • 🚀Quick Start • 📝Citation 📖Overview In this paper, we draw on pair programming practices to propose PairCoder, a novel LLM-based framework for code generation. PairCoder incorporates two collaborative LLM agents, namely a Navigator agent for high-level planning and a Driver agent for specific implementation.
| Stars | 111 |
| Forks | 13 |
| Language | Python |
| Category | Agent Tool |
| License | GPL-3.0 |
| Quality Score | 65.2182040141094/100 |
| Last Updated | 2024-11-29 |
| Created | 2024-08-18 |
| Platforms | python |
| Est. Tokens | ~1506k |
These tools work well together with PairCoder for enhanced workflows:
Explore other popular agent tool tools:
PairCoder is A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement, ASE 2024 (Distinguished Paper Award). It is categorized as a Agent Tool with 111 GitHub stars.
PairCoder is primarily written in Python. It covers topics such as code-generation, large-language-models, llm-agent.
You can find installation instructions and usage details in the PairCoder GitHub repository at github.com/nju-websoft/PairCoder. The project has 111 stars and 13 forks, indicating an active community.
PairCoder is released under the GPL-3.0 license, making it free to use and modify according to the license terms.