@inproceedings{vohra-xu-2026-research,
title = "Research Agents Feed Doubts, Not Beliefs: Auditing Belief Framing in Live-Web Search",
author = "Vohra, Siddharth and
Xu, Min",
editor = "Kamalloo, Ehsan and
Gontier, Nicolas and
Rozanov, Nikolai and
Hashemzadeh, Maryam and
Arora, Akhil",
booktitle = "Proceedings of the Second Workshop for {RE}search on Agent Language Models ({REALM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.realm-1.45/",
pages = "664--674",
ISBN = "979-8-89176-485-9",
abstract = "People increasingly hand fact-finding to LLM agents that search the web and return a cited report. We ask whether the belief a user states when making the request changes the research itself. We give 48 expert-verified health claims to four search-equipped agents under believer, skeptic, and neutral framings, analyzing 1,874 of 2,064 registered runs plus second-round arms reported separately. The effect is asymmetric: stating belief leaves conclusions unchanged (0.02, claim-clustered 95{\%} CI -0.04 to 0.09), while stating doubt moves them toward rejection (-0.26, CI -0.39 to -0.15). Across opposing framings the same agent{'}s conclusion shifts 0.26 points on a five-point scale (CI 0.15 to 0.40), a quarter of one label step, and every system moves the same way. The shift sits on contested claims (0.61) and is small on the settled tiers (0.10 and 0.11). Strictly opposite conclusions were rare and their registered paired test was null (p=0.250), so this is a shift in degree rather than a reversal of verdicts. The trajectories mirror it: skeptic framing more than doubles deny-seeking queries (net -9.9 points against +0.5 for believer framing). Crossing the retrieved evidence between framings splits the gap into how the agent reads what comes back (0.23, CI 0.12 to 0.34) and which evidence comes back at all (0.08, CI 0.00 to 0.16), two channels that add to the end-to-end gap by construction and put about three quarters of it on reading, though the evidence interval reaches zero. Labeling retrieved results against the claim finds no evidence that stated doubt returns a more hostile pool (1.7 points, CI -1.5 to 5.5). An indicative post-hoc follow-up on the 32 claims it reached adds a both-sides instruction to the skeptic condition, where the bias lives, and shifts conclusions by 0.16 (CI 0.04 to 0.30). We release FramedFacts-48: claims, prompts, and analyzed runs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vohra-xu-2026-research">
<titleInfo>
<title>Research Agents Feed Doubts, Not Beliefs: Auditing Belief Framing in Live-Web Search</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Vohra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Xu</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 Second Workshop for REsearch on Agent Language Models (REALM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Kamalloo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Gontier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Rozanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maryam</namePart>
<namePart type="family">Hashemzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akhil</namePart>
<namePart type="family">Arora</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">979-8-89176-485-9</identifier>
</relatedItem>
<abstract>People increasingly hand fact-finding to LLM agents that search the web and return a cited report. We ask whether the belief a user states when making the request changes the research itself. We give 48 expert-verified health claims to four search-equipped agents under believer, skeptic, and neutral framings, analyzing 1,874 of 2,064 registered runs plus second-round arms reported separately. The effect is asymmetric: stating belief leaves conclusions unchanged (0.02, claim-clustered 95% CI -0.04 to 0.09), while stating doubt moves them toward rejection (-0.26, CI -0.39 to -0.15). Across opposing framings the same agent’s conclusion shifts 0.26 points on a five-point scale (CI 0.15 to 0.40), a quarter of one label step, and every system moves the same way. The shift sits on contested claims (0.61) and is small on the settled tiers (0.10 and 0.11). Strictly opposite conclusions were rare and their registered paired test was null (p=0.250), so this is a shift in degree rather than a reversal of verdicts. The trajectories mirror it: skeptic framing more than doubles deny-seeking queries (net -9.9 points against +0.5 for believer framing). Crossing the retrieved evidence between framings splits the gap into how the agent reads what comes back (0.23, CI 0.12 to 0.34) and which evidence comes back at all (0.08, CI 0.00 to 0.16), two channels that add to the end-to-end gap by construction and put about three quarters of it on reading, though the evidence interval reaches zero. Labeling retrieved results against the claim finds no evidence that stated doubt returns a more hostile pool (1.7 points, CI -1.5 to 5.5). An indicative post-hoc follow-up on the 32 claims it reached adds a both-sides instruction to the skeptic condition, where the bias lives, and shifts conclusions by 0.16 (CI 0.04 to 0.30). We release FramedFacts-48: claims, prompts, and analyzed runs.</abstract>
<identifier type="citekey">vohra-xu-2026-research</identifier>
<location>
<url>https://aclanthology.org/2026.realm-1.45/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>664</start>
<end>674</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Research Agents Feed Doubts, Not Beliefs: Auditing Belief Framing in Live-Web Search
%A Vohra, Siddharth
%A Xu, Min
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Rozanov, Nikolai
%Y Hashemzadeh, Maryam
%Y Arora, Akhil
%S Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-485-9
%F vohra-xu-2026-research
%X People increasingly hand fact-finding to LLM agents that search the web and return a cited report. We ask whether the belief a user states when making the request changes the research itself. We give 48 expert-verified health claims to four search-equipped agents under believer, skeptic, and neutral framings, analyzing 1,874 of 2,064 registered runs plus second-round arms reported separately. The effect is asymmetric: stating belief leaves conclusions unchanged (0.02, claim-clustered 95% CI -0.04 to 0.09), while stating doubt moves them toward rejection (-0.26, CI -0.39 to -0.15). Across opposing framings the same agent’s conclusion shifts 0.26 points on a five-point scale (CI 0.15 to 0.40), a quarter of one label step, and every system moves the same way. The shift sits on contested claims (0.61) and is small on the settled tiers (0.10 and 0.11). Strictly opposite conclusions were rare and their registered paired test was null (p=0.250), so this is a shift in degree rather than a reversal of verdicts. The trajectories mirror it: skeptic framing more than doubles deny-seeking queries (net -9.9 points against +0.5 for believer framing). Crossing the retrieved evidence between framings splits the gap into how the agent reads what comes back (0.23, CI 0.12 to 0.34) and which evidence comes back at all (0.08, CI 0.00 to 0.16), two channels that add to the end-to-end gap by construction and put about three quarters of it on reading, though the evidence interval reaches zero. Labeling retrieved results against the claim finds no evidence that stated doubt returns a more hostile pool (1.7 points, CI -1.5 to 5.5). An indicative post-hoc follow-up on the 32 claims it reached adds a both-sides instruction to the skeptic condition, where the bias lives, and shifts conclusions by 0.16 (CI 0.04 to 0.30). We release FramedFacts-48: claims, prompts, and analyzed runs.
%U https://aclanthology.org/2026.realm-1.45/
%P 664-674
Markdown (Informal)
[Research Agents Feed Doubts, Not Beliefs: Auditing Belief Framing in Live-Web Search](https://aclanthology.org/2026.realm-1.45/) (Vohra & Xu, REALM 2026)
ACL