@inproceedings{chen-etal-2026-apex-searcher,
title = "{APEX}-Searcher: Hierarchical Credit Assignment with Subgoaling for Agentic Retrieval-Augmented Generation",
author = "Chen, Kun and
Kong, Qingchao and
Feifei, Zhao and
Mao, Wenji",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1538/",
pages = "32708--32726",
ISBN = "979-8-89176-462-0",
abstract = "Retrieval-augmented generation (RAG) connects large language models (LLMs) to external knowledge, but single-round retrieval is often insufficient for complex multi-hop questions. To improve search on complex tasks, most existing works combine multi-round retrieval with reasoning through end-to-end training. While these approaches improve problem-solving performance, they still face challenges in task reasoning and model training. First, due to the lack of an explicit subgoaling mechanism, most existing RAG methods may produce ambiguous retrieval execution paths, leading to the degradation of model performance. Second, a few existing RAG methods have started to incorporate planning and execution into the model training process. However, they typically rely on a single final reward, causing hierarchical credit entanglement between planning and execution and preventing the model from clearly separating plan errors from retrieval errors. To address these limitations, we propose APEX-Searcher, a coordinated planner{--}executor framework that optimizes a recursive planner with RL to accommodate multiple valid, dependency-aware decompositions while training the executor with SFT under clearer subtask-level supervision. Extensive experiments show consistent gains in both multi-hop RAG and task planning across benchmarks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-apex-searcher">
<titleInfo>
<title>APEX-Searcher: Hierarchical Credit Assignment with Subgoaling for Agentic Retrieval-Augmented Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingchao</namePart>
<namePart type="family">Kong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhao</namePart>
<namePart type="family">Feifei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenji</namePart>
<namePart type="family">Mao</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Retrieval-augmented generation (RAG) connects large language models (LLMs) to external knowledge, but single-round retrieval is often insufficient for complex multi-hop questions. To improve search on complex tasks, most existing works combine multi-round retrieval with reasoning through end-to-end training. While these approaches improve problem-solving performance, they still face challenges in task reasoning and model training. First, due to the lack of an explicit subgoaling mechanism, most existing RAG methods may produce ambiguous retrieval execution paths, leading to the degradation of model performance. Second, a few existing RAG methods have started to incorporate planning and execution into the model training process. However, they typically rely on a single final reward, causing hierarchical credit entanglement between planning and execution and preventing the model from clearly separating plan errors from retrieval errors. To address these limitations, we propose APEX-Searcher, a coordinated planner–executor framework that optimizes a recursive planner with RL to accommodate multiple valid, dependency-aware decompositions while training the executor with SFT under clearer subtask-level supervision. Extensive experiments show consistent gains in both multi-hop RAG and task planning across benchmarks.</abstract>
<identifier type="citekey">chen-etal-2026-apex-searcher</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1538/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>32708</start>
<end>32726</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T APEX-Searcher: Hierarchical Credit Assignment with Subgoaling for Agentic Retrieval-Augmented Generation
%A Chen, Kun
%A Kong, Qingchao
%A Feifei, Zhao
%A Mao, Wenji
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F chen-etal-2026-apex-searcher
%X Retrieval-augmented generation (RAG) connects large language models (LLMs) to external knowledge, but single-round retrieval is often insufficient for complex multi-hop questions. To improve search on complex tasks, most existing works combine multi-round retrieval with reasoning through end-to-end training. While these approaches improve problem-solving performance, they still face challenges in task reasoning and model training. First, due to the lack of an explicit subgoaling mechanism, most existing RAG methods may produce ambiguous retrieval execution paths, leading to the degradation of model performance. Second, a few existing RAG methods have started to incorporate planning and execution into the model training process. However, they typically rely on a single final reward, causing hierarchical credit entanglement between planning and execution and preventing the model from clearly separating plan errors from retrieval errors. To address these limitations, we propose APEX-Searcher, a coordinated planner–executor framework that optimizes a recursive planner with RL to accommodate multiple valid, dependency-aware decompositions while training the executor with SFT under clearer subtask-level supervision. Extensive experiments show consistent gains in both multi-hop RAG and task planning across benchmarks.
%U https://aclanthology.org/2026.findings-emnlp.1538/
%P 32708-32726
Markdown (Informal)
[APEX-Searcher: Hierarchical Credit Assignment with Subgoaling for Agentic Retrieval-Augmented Generation](https://aclanthology.org/2026.findings-emnlp.1538/) (Chen et al., Findings 2026)
ACL