Aug 2026· Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2· 0 citations· 7 references
TL;DR
NaviRAG is a novel framework that reformulates retrieval as a reinforcement learning-driven dynamic navigation problem on schema-less knowledge graphs (KGs), achieving state-of-the-art performance in multi-hop QA while maintaining robustness in single-hop QA.
Abstract
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.
EvoGraph-R1 is introduced, a self-evolving GraphRAG framework that reconceptualizes knowledge graphs as dynamic environments shaped through agent interactions, establishing self-evolving knowledge graphs as a fundamental paradigm across modalities.
Jiashi Lin, Changhong Jiang, Xiangru Lin et al.· 1 citation
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.
Tram Ngoc-Bao Nguyen, Truong H. V. Phan· Journal of Intelligent &...· 0 citations
Retrieval-Augmented Generation (RAG) significantly enhances the ability of Large Language Models (LLMs) to provide accurate and contextually relevant answers by dynamically integrating external databases. However, traditional RAG methods are primarily constrained by their reliance on text-based retrieval strategies, which often struggle with complex questions requiring multi-hop reasoning. To address this limitation, we introduce Neural Graph Matching based Retrieval-Augmented Generation (NGM-RAG), a novel framework that leverages graph structures to effectively capture and utilize relational knowledge for improved retrieval and answer generation. NGM-RAG explicitly incorporates graph construction, graph matching, and answer generation into a unified process. Within this framework, we propose a neural graph matching approach that combines text-based matching with Graph Neural Networks (GNNs). By employing an adaptive weighting strategy, NGM-RAG efficiently integrates multiple matching methods to select the most relevant contextual node information for answer generation. Experimental results on multi-hop question answering and long-context summarization tasks demonstrate that our NGM-RAG model achieves superior performance compared to both traditional NaiveRAG methods and state-of-the-art graph-enhanced approaches such as GraphRAG and LightRAG.
Retrieval-augmented Generation (RAG) has emerged as an effective paradigm for enhancing large language models (LLMs) with external knowledge, delivering substantial performance gains without costly parameter updates, particularly in low-resource settings. However, existing RAG systems still face several open challenges. Many approaches rely on static or heuristic retrieval strategies, limiting their ability to adapt retrieval strategies to different tasks with different reasoning requirements. Some methods build RAG systems based on independently optimized components, making joint optimization across all components infeasible. Moreover, empirical evidence shows that stronger retrievers do not necessarily lead to better end-to-end RAG performance, revealing a misalignment between retrieval quality and generation effectiveness and leaving considerable room for improvement in how retrieval is integrated into the RAG pipeline. Motivated by these challenges, we propose ARF-RAG, an Adaptive Retriever-Friendly Retrieval-Augmented Generation framework. ARF-RAG dynamically determines when to retrieve and further generates retriever-friendly queries that faithfully reflect the generator's current information needs while being optimized for the behavior of the given retriever. ARF-RAG adopts a role-unified mechanism, in which a single LLM simultaneously performs all retrieval-related and generation actions, including retrieval decision-making, query generation, and answer generation, enabling coherent optimization across all components. To effectively align the retriever and generator, we formulate RAG as a unified reinforcement learning (RL) problem. We design comprehensive reward functions that jointly account for answer correctness, retrieval effectiveness, and retrieval cost, enabling fine-grained policy optimization via proximal policy optimization (PPO). Extensive experiments. The codebase for reproducing the proposed framework is publicly available at: https://github.com/ii-research/ARF-RAG on three question-answering benchmarks demonstrate that ARF-RAG consistently outperforms strong non-RL and RL-based baselines on both simple and complex QA tasks. Further analyses show that ARF-RAG adaptively learns when to retrieve based on question complexity and generates more effective, retriever-aligned queries that resolve what to retrieve, highlighting the advantages of unified RL optimization for building robust and efficient RAG systems.
Yubo Fang, Hai-tao Yu, Hideo Joho et al.· International Conference on...· 0 citations
Multi-modal retrieval-augmented generation (RAG) is a key technique for visually rich long document understanding. Existing multi-modal RAG methods are progressively advancing toward multi-agent systems: they first retrieve relevant pages based on a query, and then iteratively understand information within those pages. However, these methods typically rely on fixed workflows and lack the ability to dynamically scale computation at test time, often leading to insufficient evidence. To address this, we propose D2-ScaleAgent, an agentic framework that introduces a dual-dimensional scaling paradigm for retrieval and reasoning. The core of D2-ScaleAgent is a Verifier agent-driven dynamic routing loop based on the intrinsic difficulty of the query, centered around a continuously updated evidence bank that serves as the agent's dynamic working memory: when retrieval needs to be expanded, the agent routes outward (retrieval scaling), decomposing the query into attributes and performing parallel page retrieval, followed by adaptive pruning to ensure comprehensive evidence coverage. When fine-grained reasoning is required, the agent routes inward (reasoning scaling), dynamically selecting sub-agents with varying granularity and count to extract evidence from pages. Finally, D2-ScaleAgent achieves logical closure over the evidence chain. Extensive experiments demonstrate that D2-ScaleAgent is effective on long and visually rich document benchmarks like MMLongBench-Doc, LongDocURL, etc.
Hao Zhang, Longrong Yang, Lunhao Duan et al.· 0 citations
Reinforcement learning (RL) search agents commonly model retrieval as free-form natural-language query generation and optimize multi-turn interactions using final-answer rewards. Current studies mainly improve training with denser or more structured credit signals, but rarely examine whether retrieval is properly formulated at the policy-environment interface. We observe pronounced retrieval aliasing during Search-R1 training: rollouts for the same question continue to generate distinct query strings, yet their accumulated evidence sets increasingly overlap. We call this phenomenon retrieval-equivalence collapse; in this regime, trajectories approach utility equivalence with respect to retrieval decisions, leaving within-group returns with little effective retrieval contrast. To address this problem, we propose Harness-G, a graph-structured retrieval framework that redesigns this interface. It reformulates free-form query generation as finite action selection: the policy selects an evidence sentence or entity, or chooses to answer, while the environment constructs the menu, tracks retrieval state, and validates and executes each choice. This interface reduces linguistic aliasing and makes same-state alternatives directly comparable. Building on this interface, we introduce Structured Non-myopic Credit (SNC), which uses a frozen answer scorer to compare the selected action with its alternatives and assigns downstream gains to the earlier actions that enabled them. Across six QA benchmarks, Harness-G achieves the highest average F1 at both evaluated model scales, outperforming the strongest baseline, Graph-R1, by 10.74 points at 1.5B and 3.98 points at 3B.
Yanning Hou, Hao-Yuan Chen, Sihang Zhou et al.· 0 citations