Are reasoning paradigms scale-aware? A cross-paradigm verification of prompting, retrieval, and knowledge-graph scaffolding for small language models

Graph-Assisted Large Language Models: A Perspective on Mitigating Intrinsic Limitations

Large language models (LLMs) have made progress in knowledge-intensive tasks, reasoning and planning, and collaborative problem solving, yet they exhibit intrinsic limitations such as knowledge cutoff, single-threaded reasoning that hinders finer-grained branch and aggregation, and rigid collaboration mechanisms that struggle to coordinate specialized capabilities. Graphs, with their ability to represent relational knowledge and complex dependencies, offer a natural means to address these limitations: they provide structured, high-density knowledge for augmenting or correcting LLMs’ generation; enable revisitable inference by organizing intermediate steps as graphs; and support dynamic coordination among experts or agents in collaborative settings. Motivated by these developments, we present the first systematic survey of graph-assisted LLMs from the perspective of how graph structures mitigate LLMs’ limitations. We introduce a taxonomy spanning Graph-Assisted Knowledge Augmentation, Graph-Assisted Reasoning and Planning, and Graph-Assisted LLM Collaboration , and analyze representative methods, summarize common design patterns, and outline open challenges and future directions for advancing LLMs with graph-based enhancements. The collected papers are available in link here.

D$^2$F-ReAG: Dynamic Decomposition and Filtering for Multi-Hop Reasoning-Augmented Generation

Large language models (LLMs) often generate inaccurate answers due to their reliance on static internal knowledge. Retrieval-augmented generation (RAG) addresses this limitation by integrating external knowledge and excelling at single-hop queries. However, it struggles with multi-hop questions that require cross-document reasoning. Existing methods, such as graph structured RAG or question decomposition, often lack dynamic decomposition and effective filtering, which leads to lower efficiency and accuracy. To overcome these limitations, we propose Dynamic Decomposition and Filtering for Multi-Hop Reasoning-Augmented Generation (D2F-ReAG), a novel paradigm that adaptively controls reasoning depth by judging the reliability of the root-level reasoning. If the root reasoning is reliable, the model directly generates the answer. Otherwise, the question is logically decomposed into sub-questions, and the verified reasoning derived from these sub-questions is used to refine the root reasoning. Experiments on three multi-hop benchmarks demonstrate the effectiveness of our method in handling complex multi-hop questions.

Better Prompts, Better Usefulness: A Systematic Review and Experimental Evaluation of Structured Prompting Techniques in Large Language Models

Large Language Models (LLMs) have rapidly become central components of cognitive computing systems and AI-assisted knowledge work. However, the effectiveness of LLM-generated outputs depends not only on the model’s capabilities but also on the structure of the prompts used to guide them. This study investigates how structured prompting techniques influence perceived output usefulness in business-oriented tasks. First, we conduct a systematic literature review following PRISMA guidelines to identify, classify, and synthesize existing prompt enhancement strategies. The review leads to the development of a taxonomy distinguishing task-alignment techniques (e.g., one-shot and few-shot prompting) from reasoning-transparency techniques (e.g., Chain-of-Thought prompting). Building on this taxonomy, we design a controlled experimental study in which knowledge workers evaluate LLM-generated outputs across analytical and summarization tasks. Using linear mixed-effects modeling, we assess the impact of prompting techniques and the moderating role of Generative AI usage frequency. Results indicate that structured prompting significantly increases perceived usefulness compared to baseline approaches, with the combination of example-based conditioning and explicit reasoning scaffolding yielding the highest evaluations. The moderating effect of usage frequency is not statistically significant, suggesting that the benefits of structured prompt design are robust across different experience levels. These findings position prompt structure as a practical cognitive interface mechanism and provide evidence-based guidelines for enhancing human–AI interaction in cognitive computing environments.

AdaKG-RAG: Adaptive KG-guided retrieval-augmented generation with hypothesis-and-verification retrieval for multi-hop question answering

Retrieval-Augmented Generation (RAG) has improved the factual grounding of large language models, but multi-hop question answering remains challenging because a system may retrieve semantically relevant yet evidence-incomplete contexts. Existing KG-guided RAG methods improve evidence coverage through graph expansion, but they often operate in a single-pass manner and lack an explicit mechanism for judging whether the assembled evidence is sufficient for reliable reasoning. Therefore, we propose AdaKG-RAG, an evidence-sufficiency-driven KG-guided RAG framework for multi-hop question answering. The core of AdaKG-RAG is a Hypothesis-and-Verification Retrieval (HVR) loop, which first forms a tentative answer from the current evidence, verifies whether the evidence is sufficient, and triggers targeted retrieval refinement when bridge facts are missing. To support this loop, AdaKG-RAG uses semantic-aware KG expansion and path-aware evidence organization to recover and structure candidate bridge evidence, followed by answer-aware supporting-fact (SF) reranking for better answer–evidence alignment. Experiments on HotpotQA and MuSiQue, together with a long-context evaluation on TriviaQA, show that AdaKG-RAG improves both answer quality and evidence retrieval quality over representative RAG and KG-RAG baselines. Further analysis indicates that HVR contributes the largest performance gain, while graph-based modules provide complementary improvements in evidence coverage and organization.

Multi-model relevance-guided reverse reasoning: improving chain-of-thought with small models

Architecting Reliable Knowledge Retrieval Systems Using Large Language Models

The increasing deployment of large language models (LLMs) in enterprise environments creates reliability challenges related to hallucination, factual inconsistency, limited knowledge traceability, uncertainty, and operational efficiency. This study develops a literature-based architectural framework for reliable knowledge retrieval systems that separates external knowledge management from LLM-based reasoning and generation. The framework synthesizes architectural mechanisms for knowledge representation, hybrid retrieval, reranking, evidence selection, context construction, response verification, provenance tracking, uncertainty handling, guardrails, and computational efficiency. The resulting architecture organizes these mechanisms into coordinated layers that control the flow of external evidence from knowledge sources to generated responses while supporting traceability and controlled abstention when sufficient evidence is unavailable. The architectural synthesis further identifies complementary strategies for enterprise deployment, including semantic caching, model routing, and human oversight, to balance reliability, scalability, and operational cost. The analysis indicates that reliable LLM deployment should be treated as an end-to-end architectural problem rather than solely a model-performance problem, with knowledge access, evidence quality, verification, provenance, and governance functioning as integrated system components. The proposed framework provides a structured foundation for designing maintainable, auditable, and reliable knowledge retrieval systems for enterprise and other high-stakes applications