Large Language Models (LLMs) have shown remarkable advancements in specialized fields such as finance, law, and medicine.However, in cybersecurity, we have noticed a lack of opensource datasets, with a particular lack of highquality cybersecurity pretraining corpora, even though much research indicates that LLMs acquire their knowledge during pretraining.To address this, we present a comprehensive suite of datasets covering all major training stages, including pretraining, instruction fine-tuning, and reasoning distillation with cybersecurityspecific self-reflection data.Extensive ablation studies demonstrate their effectiveness on public cybersecurity benchmarks.In particular, continued pre-training on our dataset yields a 15.9% improvement in the aggregate score, while reasoning distillation leads to a 15.8% gain in security certification (CISSP).We will release all datasets and trained cybersecurity LLMs under the ODC-BY and MIT licenses to encourage further research in the community.10 41 4 1 3 2 1 1 1 Natural Language Non-Natural Language General LLM Cybersecurity LLM Cybersecurity Instruction Following, including alert explanation, suspicious command analysis, and security query generation… PT Studies CTI-BERT CyBERT SecBERT SecureBERT Primus(ours) Released Datasets No No No No Yes Exp Arch Bert

Conventional retrieval-augmented generation(RAG) systems employ rigid retrieval strategies that create: (1) knowledge blind spots across domain boundaries, (2) reasoning fragmentation when processing interdependent concepts, and (3) contradictions from conflicting evidence sources. Motivated by these limitations, we introduce PathwiseRAG, which addresses these challenges through: intent-aware strategy selection to eliminate blind spots, dynamic reasoning networks that capture sub-problem interdependencies to overcome fragmentation, and parallel path exploration with adaptive refinement to resolve conflicts. The framework models query intent across semantic and reasoning dimensions, constructs a directed acyclic graph of interconnected sub-problems, and explores multiple reasoning trajectories while continuously adapting to emerging evidence. Evaluation across challenging benchmarks demonstrates significant improvements over state-of-the-art RAG systems, with average accuracy gains of 4.9% and up to 6.9% on complex queries, establishing a new paradigm for knowledge-intensive reasoning by transforming static retrieval into dynamic, multi-dimensional exploration.