Work

Multi-Agent Reinforcement Learning for Interactive Code Debugging with Human Feedback and Memory

Year: 2025
Type: conference-paper
Abstract: This paper introduces an interactive Python debugging framework that combines multi-agent reinforcement learning, Natural Language Processing (NLP), and long-term memory.Two Proximal Policy Optimization (PPO) agents specialize in syntax and logic errors, generating candidate fixes that developers can accept, reject, or refine.A BERT-based module encodes natural language feedback into dense embeddings and quality scores, which shape reward signals for Reinforcement Learning from Human Feedback (RLHF).To support personalization, the system uses dual FAISS indices to retrieve past fixes based on codeerror pairs and developer explanations.Evaluated on a synthetic dataset of 200 Python programs, our approach achieves an 88% syntaxfix rate and 45% logic-fix rate within five suggestions-outperforming one-shot Large Language Model (LLM) baselines.In addition, the system improves the quality of the explanation, as measured by BLEU, ROUGE, and Code-BLEU.By integrating multi-agent specialization, linguistic feedback, and memory-driven retrieval, our framework delivers a more efficient, adaptive, and developer-aligned debugging experience.
Language: English
Open Access status: bronze
OpenAlex ID: W7124153392
FWCI: 1.05
Cites: 7
Cited by: 3
Related to: 10