@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://aclanthology.org/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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-par2">
<titleInfo>
<title>PAR²-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xingyu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rongguang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuying</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengqing</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenyang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Sheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujith</namePart>
<namePart type="family">Ravi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Roth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-394-4</identifier>
</relatedItem>
<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 Planned Active Retrieval and Reasoning RAG (PAR²-RAG), a training-free two-stage framework that separates coverage from commitment. PAR²-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, PAR²-RAG consistently outperforms strong baselines: compared with IRCoT, it achieves up to 23.5% higher answer accuracy and up to 10.5% NDCG gains in retrieval quality.</abstract>
<identifier type="citekey">li-etal-2026-par2</identifier>
<location>
<url>https://aclanthology.org/2026.acl-industry.118/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1727</start>
<end>1737</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PAR²-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering
%A Li, Xingyu
%A Wang, Rongguang
%A Wang, Yuying
%A Guo, Mengqing
%A Li, Chenyang
%A Sheng, Tao
%A Ravi, Sujith
%A Roth, Dan
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F li-etal-2026-par2
%X 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 Planned Active Retrieval and Reasoning RAG (PAR²-RAG), a training-free two-stage framework that separates coverage from commitment. PAR²-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, PAR²-RAG consistently outperforms strong baselines: compared with IRCoT, it achieves up to 23.5% higher answer accuracy and up to 10.5% NDCG gains in retrieval quality.
%U https://aclanthology.org/2026.acl-industry.118/
%P 1727-1737
Markdown (Informal)
[PAR2-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering](https://aclanthology.org/2026.acl-industry.118/) (Li et al., ACL 2026)
ACL
- Xingyu Li, Rongguang Wang, Yuying Wang, Mengqing Guo, Chenyang Li, Tao Sheng, Sujith Ravi, and Dan Roth. 2026. PAR2-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), pages 1727–1737, San Diego, California, USA. Association for Computational Linguistics.