<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhong-etal-2026-self">
    <titleInfo>
        <title>Self-Correcting Agentic RAG via Memory-Grounded Failure Localization</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Haoyang</namePart>
        <namePart type="family">Zhong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yifei</namePart>
        <namePart type="family">Sun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shiwei</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jie</namePart>
        <namePart type="family">li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chunping</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Agentic RAG, which decomposes a complex question into dependency-aware sub-questions, has become the dominant paradigm for multi-hop QA. Yet existing systems can only repair errors at the failed step or simply return to the previous step and retry, and thus fail to handle two pervasive failure modes: inaccurate decomposition, where the plan is flawed before execution begins, and error propagation, where an upstream mistake surfaces downstream. We propose that addressing both requires global self-correction, the ability to identify the root cause of a failure and repair it at the right location. To this end, we propose **LoCoRAG**, a globally self-correcting agentic RAG framework. LoCoRAG maintains a persistent dual memory through a two-stage thinker-generator pipeline, separating what the corpus contains from what the system has concluded. Then, a memory-grounded failure localization module attributes each failure to specific causes and pinpoints its true origin. Together, LoCoRAG drives a self-correcting global replan that selects a matched repair, from local refinement to upstream rollback with downstream regeneration. Across existing multi-hop QA benchmarks, LoCoRAG achieves SOTA performance on all datasets and all metrics, with a 10.8 points average LLM-Acc gain over the strongest baseline on 3-hop-or-deeper scenarios.</abstract>
    <identifier type="citekey">zhong-etal-2026-self</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2183/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>49629</start>
            <end>49652</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Self-Correcting Agentic RAG via Memory-Grounded Failure Localization
%A Zhong, Haoyang
%A Sun, Yifei
%A Liu, Shiwei
%A li, Jie
%A Wang, Chunping
%A Yang, Yang
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F zhong-etal-2026-self
%X Agentic RAG, which decomposes a complex question into dependency-aware sub-questions, has become the dominant paradigm for multi-hop QA. Yet existing systems can only repair errors at the failed step or simply return to the previous step and retry, and thus fail to handle two pervasive failure modes: inaccurate decomposition, where the plan is flawed before execution begins, and error propagation, where an upstream mistake surfaces downstream. We propose that addressing both requires global self-correction, the ability to identify the root cause of a failure and repair it at the right location. To this end, we propose **LoCoRAG**, a globally self-correcting agentic RAG framework. LoCoRAG maintains a persistent dual memory through a two-stage thinker-generator pipeline, separating what the corpus contains from what the system has concluded. Then, a memory-grounded failure localization module attributes each failure to specific causes and pinpoints its true origin. Together, LoCoRAG drives a self-correcting global replan that selects a matched repair, from local refinement to upstream rollback with downstream regeneration. Across existing multi-hop QA benchmarks, LoCoRAG achieves SOTA performance on all datasets and all metrics, with a 10.8 points average LLM-Acc gain over the strongest baseline on 3-hop-or-deeper scenarios.
%U https://aclanthology.org/2026.emnlp-main.2183/
%P 49629-49652

Markdown (Informal)

[Self-Correcting Agentic RAG via Memory-Grounded Failure Localization](https://aclanthology.org/2026.emnlp-main.2183/) (Zhong et al., EMNLP 2026)

• Self-Correcting Agentic RAG via Memory-Grounded Failure Localization (Zhong et al., EMNLP 2026)

ACL

• Haoyang Zhong, Yifei Sun, Shiwei Liu, Jie li, Chunping Wang, and Yang Yang. 2026. Self-Correcting Agentic RAG via Memory-Grounded Failure Localization. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 49629–49652, Budapest, Hungary. Association for Computational Linguistics.