MeAI++: Improving answer quality with reinforcement learning for graph retrieval-augmented generation

Retrieval-Augmented Generation (RAG) improves the factual grounding of large language models but still suffers from noisy retrieval, limited multi-hop reasoning, and lack of adaptive optimization. This paper proposes MeAI++, a novel framework that integrates knowledge graph based retrieval with a reinforcement learning (RL) optimization loop to jointly enhance retrieval and generation. Specifically, retrieved documents are structured into a knowledge graph to enable interpretable multi-hop reasoning, while an RL-based policy iteratively refines query rewriting, context selection, and response generation using a multi-objective reward function (semantic similarity, factual correctness, coherence, and fluency). Experimental results on 2WikiMultihopQA, ASQA, and PubMedQA demonstrate that MeAI++ significantly outperforms state-of-the-art RAG models, achieving up to 75.18 F1 on 2WikiMultihopQA and 74.49 F1 on PubMedQA, along with substantial gains in BLEU-1 and ROUGE-L for answer generation. These results confirm the effectiveness and generalizability of MeAI++ for complex, knowledge-intensive question answering.