@inproceedings{zhu-2026-combining,
title = "Combining {RAG} and Agentic Research for Evidence-Grounded Scientific Question Answering",
author = "Zhu, Zhirui",
editor = "Wang, Yimu and
Choi, Yee Man and
Wu, Di and
Ouyang, Siqi and
Azadani, Mozhgan Nasr and
Fung, Yi R. (May)",
booktitle = "Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently ({G}round{LM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.groundlm-1.84/",
pages = "1168--1173",
ISBN = "979-8-89176-478-1",
abstract = "We present ThousandOfWind{'}s hybrid system for GroundLM 2026 LitTraceQA, combining traditional retrieval-augmented generation (RAG) with code-agent research. Agents design question-specific search scripts, revise them as evidence emerges, and reconcile their findings with RAG candidates. The required-test configuration starts with independent research and accepts subsequent revisions through field-level confidence gates and table-structure checks. Using GPT-5.6 Terra in GitHub Copilot CLI, the system raises the 71-question test composite from 0.3567 to 0.7374 and multiple-choice accuracy from 18/50 to 50/50. Macro table cell accuracy reaches 0.2698, leaving structured assembly as the main bottleneck. Our analysis explains the limits of row-key-preserving repair and motivates source-supported structural editing."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-2026-combining">
<titleInfo>
<title>Combining RAG and Agentic Research for Evidence-Grounded Scientific Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhirui</namePart>
<namePart type="family">Zhu</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 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yimu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yee</namePart>
<namePart type="given">Man</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siqi</namePart>
<namePart type="family">Ouyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mozhgan</namePart>
<namePart type="given">Nasr</namePart>
<namePart type="family">Azadani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="given">R</namePart>
<namePart type="given">(May)</namePart>
<namePart type="family">Fung</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">979-8-89176-478-1</identifier>
</relatedItem>
<abstract>We present ThousandOfWind’s hybrid system for GroundLM 2026 LitTraceQA, combining traditional retrieval-augmented generation (RAG) with code-agent research. Agents design question-specific search scripts, revise them as evidence emerges, and reconcile their findings with RAG candidates. The required-test configuration starts with independent research and accepts subsequent revisions through field-level confidence gates and table-structure checks. Using GPT-5.6 Terra in GitHub Copilot CLI, the system raises the 71-question test composite from 0.3567 to 0.7374 and multiple-choice accuracy from 18/50 to 50/50. Macro table cell accuracy reaches 0.2698, leaving structured assembly as the main bottleneck. Our analysis explains the limits of row-key-preserving repair and motivates source-supported structural editing.</abstract>
<identifier type="citekey">zhu-2026-combining</identifier>
<location>
<url>https://aclanthology.org/2026.groundlm-1.84/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1168</start>
<end>1173</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Combining RAG and Agentic Research for Evidence-Grounded Scientific Question Answering
%A Zhu, Zhirui
%Y Wang, Yimu
%Y Choi, Yee Man
%Y Wu, Di
%Y Ouyang, Siqi
%Y Azadani, Mozhgan Nasr
%Y Fung, Yi R. (May)
%S Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-478-1
%F zhu-2026-combining
%X We present ThousandOfWind’s hybrid system for GroundLM 2026 LitTraceQA, combining traditional retrieval-augmented generation (RAG) with code-agent research. Agents design question-specific search scripts, revise them as evidence emerges, and reconcile their findings with RAG candidates. The required-test configuration starts with independent research and accepts subsequent revisions through field-level confidence gates and table-structure checks. Using GPT-5.6 Terra in GitHub Copilot CLI, the system raises the 71-question test composite from 0.3567 to 0.7374 and multiple-choice accuracy from 18/50 to 50/50. Macro table cell accuracy reaches 0.2698, leaving structured assembly as the main bottleneck. Our analysis explains the limits of row-key-preserving repair and motivates source-supported structural editing.
%U https://aclanthology.org/2026.groundlm-1.84/
%P 1168-1173
Markdown (Informal)
[Combining RAG and Agentic Research for Evidence-Grounded Scientific Question Answering](https://aclanthology.org/2026.groundlm-1.84/) (Zhu, GroundLM 2026)
ACL