5arXiv cs.CL (Computation and Language)·
GLM-RAG: Graph Language Model retrievers outperform GNNs and vector search on out-of-domain multi-hop reasoning
A new arXiv preprint introduces GLM-RAG, a retrieval-augmented generation framework using graph language model (GLM)-based retrievers over knowledge graphs. The authors compare GLM-based, GNN-based, and vector-search retrievers across single- and multi-hop QA settings, finding that finetuned GLM retrievers generalize better to unseen domains and achieve state-of-the-art on two multi-hop benchmarks. GNN-based retrievers offer better graph coverage with efficient training, while vector search excels at single-hop tasks. The work provides a systematic comparison of retriever architectures for knowledge-graph RAG with practical implications for domain transfer.
Related guides (2)
Related events (8)
DualG-MRAG: Dual-tier graph architecture decouples macro-reasoning and micro-matching for multimodal RAG
A new arXiv preprint introduces DualG-MRAG, a framework for Multimodal Retrieval-Augmented Generation that separates global structural reasoning (Macro Graph) from fine-grained local evidence matching (Micro Graph) to address retrieval noise in multi-hop reasoning tasks. The system uses a GNN-based retriever with query-driven message passing and a dynamic programming decoding mechanism that extracts explicit reasoning paths from the GNN's forward pass rather than feeding isolated document chunks to the generative model. Experiments show improvements over baselines on evidence recall and complex QA accuracy. The work targets a known failure mode of graph-enhanced MM-RAG systems where fine-grained visual features cause graph explosion and noise.
HKVM-RAG: Hypergraph key-value separation improves multi-hop retrieval-augmented generation
A new arXiv preprint introduces HKVM-RAG, an evidence-organization layer for multi-hop RAG that uses weighted hyperedges as retrieval keys while retaining passage text as answer values. Under a fixed-substrate protocol controlling for tuple cache, reader, and evaluation budget, the hypergraph key-value approach improves over KG-PPR by +3.4 F1 on 2WikiMultiHopQA and +3.6 F1 on MuSiQue. A dense-aware controller combining frozen ColBERTv2 with HKVM features reaches 88.8, 65.1, and 85.8 F1 on three benchmarks, outperforming ColBERTv2 alone by 5–11 F1 points. The work positions hypergraph organization as a reusable evidence-control mechanism rather than a dense-retrieval replacement.
RSF-GLLM: Differentiable graph reasoning framework for multi-hop knowledge graph QA
RSF-GLLM is a new framework for multi-hop question answering over knowledge graphs that decouples differentiable graph reasoning from LLM-based answer generation. The core Recurrent Soft-Flow (RSF) module uses a GRU-guided query updater with dynamic gating to traverse semantically dissimilar bridge nodes, with flow sparsity regularization guaranteeing convergence to discrete reasoning paths. Extracted paths are textualized to fine-tune an LLM, grounding generation in factual graph topology. Experiments on WebQSP and CWQ benchmarks show competitive accuracy with improved inference efficiency over LLM-heavy baselines.
RAGU: Open-source GraphRAG engine with compact 7B extractor model outperforming 32B baseline
RAGU is a new open-source modular GraphRAG engine that separates knowledge graph extraction from consolidation, using two-stage typed extraction, DBSCAN-backed deduplication, LLM summarization, and Leiden community detection. The authors train Meno-Lite-0.1, a 7B model specialized for language skills, which outperforms Qwen2.5-32B on knowledge-graph construction by 12.5% relative harmonic mean while matching it on English GraphRAG tasks. On GraphRAG-Bench (Medical), RAGU achieves evidence recall up to 0.84 versus ≤0.76 for competing systems. The system is MIT-licensed, pip-installable, and runs on a single GPU.
RL-trained LLMs learn retriever-specific query formulation strategies for RAG
A new arXiv paper presents the first systematic study of using reinforcement learning to teach LLMs to adapt query formulation strategies to different retrieval backends. The authors find that different retrievers have surprisingly distinct optimal query styles (e.g., descriptive vs. question-like), making cross-retriever strategy transfer ineffective. They introduce a branching-based rollout technique to stabilize training over multi-step retrieval trajectories and show gains from retriever-specific human guidance and model scaling.
Comparative framework for RAG variants: when GraphRAG and Agentic RAG are actually needed
A new arXiv preprint introduces a systematic evaluation framework comparing nine standardized RAG scenarios across regular RAG, GraphRAG, Modular RAG, and Agentic RAG on semi-structured knowledge bases. The authors propose a novel context engineering method that reduces token usage by 19–53% for GraphRAG and Agentic RAG by addressing context/memory overflow. A key finding is a 'retrieval-generation gap' where expanded retrieval does not proportionally improve generation quality, suggesting retrieval-oriented metrics overstate the benefits of advanced retrieval. The work targets practitioners building production RAG systems and provides data-driven guidance on when to use each variant.
UMG-RAG: Training-free hybrid retrieval with uncertainty-aware granularity fusion for long-document RAG
Researchers propose Uncertainty-aware Multi-Granularity RAG (UMG-RAG), a training-free hybrid retrieval framework that addresses the tension between large and fine-grained retrieval chunks in RAG pipelines. The system converts dense and sparse retriever scores across multiple chunk granularities into evidence distributions, estimates reliability via entropy, and fuses candidates using query-specific confidence signals. A variant called UMGP-RAG uses fine-grained hits to locate evidence while returning broader parent chunks for coherence. Experiments on QA benchmarks show improved generation quality with no changes to the underlying retriever or generator.
RA-RFT: Retrieval-Augmented Reinforcement Fine-Tuning teaches LLMs to reason by analogy
Researchers propose Retrieval-Augmented Reinforcement Fine-Tuning (RA-RFT), a post-training framework that trains a retriever to rank contexts by expected reasoning benefit rather than semantic similarity, then fine-tunes a policy model via reinforcement learning using retrieved analogous demonstrations. The key insight is that reasoning-relevant retrieval surfaces complementary solution strategies rather than superficially similar problems. On mathematical reasoning benchmarks, RA-RFT improves AIME 2025 average@32 accuracy by 7.1 and 2.8 points over GRPO for Qwen3-1.7B and Qwen3-4B respectively, suggesting reasoning-aware retrieval is orthogonal to reward design and training curriculum improvements.