Jul 2026· Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology· 0 citations· 22 references
TL;DR
MeAI++ is proposed, a novel framework that integrates knowledge graph based retrieval with a reinforcement learning (RL) optimization loop to jointly enhance retrieval and generation and confirms the effectiveness and generalizability of MeAI++ for complex, knowledge-intensive question answering.
Abstract
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.
NGM-RAG is introduced, a novel framework that leverages graph structures to effectively capture and utilize relational knowledge for improved retrieval and answer generation and proposes a neural graph matching approach that combines text-based matching with Graph Neural Networks (GNNs).
Guo Chen, Ziwen Li, Mao Zheng et al.· arXiv.org· 0 citations
Retrieval-Augmented Generation (RAG) has become a fundamental paradigm for enhancing Large Language Models (LLMs) with external knowledge. However, while recent structure-augmented approaches organize documents into graphs to improve information access, their retrieval strategies remain largely static, relying on similarity ranking or static probability diffusion. We identify that this paradigm suffers from two inherent limitations in complex reasoning: popularity bias, where retrieval paths are trapped by high-degree distractors, and signal decay, where relevance signals attenuate over long reasoning chains. To overcome these challenges, we propose NaviRAG, a novel framework that reformulates retrieval as a reinforcement learning-driven dynamic navigation problem on schema-less knowledge graphs (KGs). Unlike passive diffusion, NaviRAG employs an agent that actively traverses the graph to act as a search-space pruning engine, identifying logical multi-hop reasoning paths. Technically, we introduce three key components: (1) Structure-Aware Query Expansion, which bridges the modality gap between unstructured queries and structured graph seeds for precise initialization; (2) Target-Driven Reward Shaping, which provides dense supervision based on semantic progress toward gold documents, effectively mitigating the sparse reward problem in large-scale graph traversal; and (3) a Multi-View Hybrid Reranking strategy that operates on the highly-pruned candidate subgraph, integrating policy confidence, semantic relevance, and global structural importance to ensure robust candidate selection. Extensive experiments on three multi-hop QA datasets and two single-hop QA datasets demonstrate that NaviRAG significantly outperforms baselines, achieving state-of-the-art performance in multi-hop QA while maintaining robustness in single-hop QA. Our code and data are available at https://github.com/CkingEW/NaviRAG.
Jinghong Lei, Wang Kun, Zhigang Chen et al.· Proceedings of the 32nd ACM...· 0 citations
This study proposes STaR, a novel retriever fine-tuning framework that integrates BM25 similarity graph-based soft labeling with a triplet similarity learning strategy based on Sentence-BERT (SBERT), and introduces a triplet-aware SBERT training architecture that explicitly models relative semantic distances between queries and candidate passages, significantly enhancing retrieval ranking precision and semantic robustness.
Jiali Jiang, Chih-Yung Chang, Youxi Li et al.· Multimedia Systems· 0 citations
Flat retrieval-augmented generation treats a corpus as a bag of chunks, discarding document hierarchy and cross document structure. We introduce SearchWiki, a harness framework that synthesizes a corpus into a hierarchical, typed, navigable wiki and trains an agent, WikiResearcher-9B, to retrieve information through multi-turn tool use. The wiki organizes knowledge into three layers - document overviews, cross- document topic pages, and page-level source records; enabling progressive refinement of retrieval when initial lookup misses. We optimize the agent's navigation policy with on-policy reinforcement learning with a multi-component reward function balancing answer correctness, retrieval quality and trajectory efficiency. Evaluation on ViDoRe-V3 (8 domains), FinanceBench, and memory benchmarks (LoCoMo, LongMemEval, PersonaMem-v2) shows that WikiResearcher- 9B which is our RL-tuned Qwen 9B model, significantly outperforms same-size untrained baselines and exceeds or matches larger external models. SearchWiki paired with WikiResearcher-9B demonstrates that learned navigation over structured corpora is a superior alternative to flat retrieval.
Guransh Singh, Vishwajeet Kumar, Arkadeep Acharya et al.· 0 citations
This work presents \textsc{GTA-RAG}, a graph-trajectory-augmented RL framework for multi-turn retrieval-augmented reasoning that consistently outperforms RL-based RAG baselines with both Qwen2.5-3B and Qwen2.5-7B backbones, while substantially improving evidence-chain coverage.
Jun Chen, Yongchao Liu, Pengyu Qiu et al.· 0 citations
This work introduces a GLM-based retriever and investigates the comparative strengths of GLM-based, GNN-based, and traditional vector-search-based retrievers in single- and multi-hop RAG settings, and suggests that finetuned GLM retrievers generalize better out of domain.
