Co-Learning: Code Learning for Multi-Agent Reinforcement Collaborative Framework with Conversational Natural Language Interfaces
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917767186219008 |
|---|---|
| author | Yu, Jiapeng Wu, Yuqian Zhan, Yajing Guo, Wenhao Xu, Zhou Lee, Raymond |
| author_facet | Yu, Jiapeng Wu, Yuqian Zhan, Yajing Guo, Wenhao Xu, Zhou Lee, Raymond |
| contents | Online question-and-answer (Q\&A) systems based on the Large Language Model (LLM) have progressively diverged from recreational to professional use. This paper proposed a Multi-Agent framework with environmentally reinforcement learning (E-RL) for code correction called Code Learning (Co-Learning) community, assisting beginners to correct code errors independently. It evaluates the performance of multiple LLMs from an original dataset with 702 error codes, uses it as a reward or punishment criterion for E-RL; Analyzes input error codes by the current agent; selects the appropriate LLM-based agent to achieve optimal error correction accuracy and reduce correction time. Experiment results showed that 3\% improvement in Precision score and 15\% improvement in time cost as compared with no E-RL method respectively. Our source code is available at: https://github.com/yuqian2003/Co_Learning |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_00985 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Co-Learning: Code Learning for Multi-Agent Reinforcement Collaborative Framework with Conversational Natural Language Interfaces Yu, Jiapeng Wu, Yuqian Zhan, Yajing Guo, Wenhao Xu, Zhou Lee, Raymond Software Engineering Artificial Intelligence Computation and Language Online question-and-answer (Q\&A) systems based on the Large Language Model (LLM) have progressively diverged from recreational to professional use. This paper proposed a Multi-Agent framework with environmentally reinforcement learning (E-RL) for code correction called Code Learning (Co-Learning) community, assisting beginners to correct code errors independently. It evaluates the performance of multiple LLMs from an original dataset with 702 error codes, uses it as a reward or punishment criterion for E-RL; Analyzes input error codes by the current agent; selects the appropriate LLM-based agent to achieve optimal error correction accuracy and reduce correction time. Experiment results showed that 3\% improvement in Precision score and 15\% improvement in time cost as compared with no E-RL method respectively. Our source code is available at: https://github.com/yuqian2003/Co_Learning |
| title | Co-Learning: Code Learning for Multi-Agent Reinforcement Collaborative Framework with Conversational Natural Language Interfaces |
| topic | Software Engineering Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2409.00985 |