PAR$^2$-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering

View PDF HTML (experimental)

Abstract:Large language models (LLMs) remain brittle on multi-hop question answering (MHQA), where answering requires combining evidence across documents through retrieval and reasoning. Iterative retrieval systems can fail by locking onto an early low-recall trajectory and amplifying downstream errors, while planning-only approaches may produce static query sets that cannot adapt when intermediate evidence changes. We propose \textbf{Planned Active Retrieval and Reasoning RAG (PAR$^2$-RAG)}, a two-stage framework that separates \emph{coverage} from \emph{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. Across four MHQA benchmarks, PAR$^2$-RAG consistently outperforms existing state-of-the-art baselines, compared with IRCoT, PAR$^2$-RAG achieves up to \textbf{23.5%} higher accuracy, with retrieval gains of up to \textbf{10.5%} in NDCG.

Comments: 11 pages, 2 figures

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2603.29085 [cs.AI]

(or arXiv:2603.29085v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2603.29085

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Xingyu Li [view email] [v1] Mon, 30 Mar 2026 23:52:54 UTC (704 KB)