@inproceedings{li-etal-2026-par2,
    title = "{PAR}$^2$-{RAG}: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering",
    author = "Li, Xingyu  and
      Wang, Rongguang  and
      Wang, Yuying  and
      Guo, Mengqing  and
      Li, Chenyang  and
      Sheng, Tao  and
      Ravi, Sujith  and
      Roth, Dan",
    editor = "Li, Yunyao  and
      Rehm, Georg  and
      Tu, Mei",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-industry.118/",
    pages = "1727--1737",
    ISBN = "979-8-89176-394-4",
    abstract = "Multi-hop question answering (MHQA) is a practical bottleneck in industry applications such as enterprise assistants, customer-support copilots, and compliance analysis, where systems must combine evidence across multiple documents before answering. Large language models (LLMs) remain brittle in this setting: iterative retrieval can commit too early to low-recall trajectories, while planning-only approaches can produce static query sets that fail to adapt when intermediate evidence changes. We propose \textbf{Planned Active Retrieval and Reasoning RAG (PAR$^2$-RAG)}, a training-free two-stage framework that separates \textit{coverage} from \textit{commitment}. PAR$^2$-RAG first performs breadth-first anchoring to build a high-recall evidence frontier, then applies depth-first refinement with evidence sufficiency control in an iterative loop. This design targets deployment constraints by avoiding retraining cycles, reducing maintenance overhead under changing corpora, and improving scalability across domains. Across four MHQA benchmarks, PAR$^2$-RAG consistently outperforms strong baselines: compared with IRCoT, it achieves up to \textbf{23.5{\%}} higher answer accuracy and up to \textbf{10.5{\%}} NDCG gains in retrieval quality."
}