Co-Learning: Code Learning for Multi-Agent Reinforcement Collaborative Framework with Conversational Natural Language Interfaces

2024/09/02 by Yu, Jiapeng, Wu, Yuqian, Zhan, Yajing +3 · 3 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Software Engineering (cs.SE)

paper · doi:10.48550/arxiv.2409.00985

Abstract

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

Cited by

• Beyond Regularity: Modeling Chaotic Mobility Patterns for Next Location Prediction
• Evaluating the Effectiveness of Large Language Models in Solving Simple Programming Tasks: A User-Centered Study
• MARCO: Multi-Agent Code Optimization with Real-Time Knowledge Integration for High-Performance Computing

Related

• Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and Improve
• LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions
• Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning
• MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning
• Advancing Language Multi-Agent Learning with Credit Re-Assignment for Interactive Environment Generalization