@inproceedings{zhang-etal-2025-pathwiserag,
    title = "{P}athwise{RAG}: Multi-Dimensional Exploration and Integration Framework",
    author = "Zhang, Hengrui  and
      Huang, Pin-Siang  and
      Zhang, Zhen  and
      Lin, Peican  and
      Yu, Yao-Ching  and
      Hu, Bo  and
      Du, Yulu",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1167/",
    pages = "22915--22936",
    ISBN = "979-8-89176-332-6",
    abstract = "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."
}