@inproceedings{ranaldi-pucci-2026-learning,
title = "Learning Multilingual Agentic Policy to Control Sycophancy",
author = "Ranaldi, Leonardo and
Pucci, Giulia",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-long.169/",
pages = "3664--3681",
ISBN = "979-8-89176-380-7",
abstract = "Large Language Models (LLMs) are highly effective at adapting to users' styles, preferences, and contextual signals{---}a property that underlies much of their practical usefulness, but which can even manifest as sycophancy, i.e., alignment with user-implied beliefs evenwhen these contradict factual accuracy or rational reasoning. Prior work treats sycophancy as a surface-level artefact addressed via inference-time or post-hoc methods. We argue that it is a policy-level failure arising from missing agentic control over agreement under pressure. To make sycophancy amenable to explicit control, we propose learning agentic policies modelling LLMs' behaviour as a decision-making problem. Our approach equips a single model with an explicit action space that includes answering directly, countering misleading signals, or asking for clarification. The policy is trained to optimise a multi-objective reward that balances task success, sycophancy resistance, and behavioural consistency via a control mechanism that operates through agentic behaviour. We evaluate the method on different benchmarks, showing that the approaches reduce sycophancy, improving performance, and generalise robustly across languages. These findings suggest that mitigating sycophancy requires moving beyond compliance-oriented generation towards agreement-agentic control."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ranaldi-pucci-2026-learning">
<titleInfo>
<title>Learning Multilingual Agentic Policy to Control Sycophancy</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leonardo</namePart>
<namePart type="family">Ranaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giulia</namePart>
<namePart type="family">Pucci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-380-7</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) are highly effective at adapting to users’ styles, preferences, and contextual signals—a property that underlies much of their practical usefulness, but which can even manifest as sycophancy, i.e., alignment with user-implied beliefs evenwhen these contradict factual accuracy or rational reasoning. Prior work treats sycophancy as a surface-level artefact addressed via inference-time or post-hoc methods. We argue that it is a policy-level failure arising from missing agentic control over agreement under pressure. To make sycophancy amenable to explicit control, we propose learning agentic policies modelling LLMs’ behaviour as a decision-making problem. Our approach equips a single model with an explicit action space that includes answering directly, countering misleading signals, or asking for clarification. The policy is trained to optimise a multi-objective reward that balances task success, sycophancy resistance, and behavioural consistency via a control mechanism that operates through agentic behaviour. We evaluate the method on different benchmarks, showing that the approaches reduce sycophancy, improving performance, and generalise robustly across languages. These findings suggest that mitigating sycophancy requires moving beyond compliance-oriented generation towards agreement-agentic control.</abstract>
<identifier type="citekey">ranaldi-pucci-2026-learning</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-long.169/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>3664</start>
<end>3681</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Multilingual Agentic Policy to Control Sycophancy
%A Ranaldi, Leonardo
%A Pucci, Giulia
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-380-7
%F ranaldi-pucci-2026-learning
%X Large Language Models (LLMs) are highly effective at adapting to users’ styles, preferences, and contextual signals—a property that underlies much of their practical usefulness, but which can even manifest as sycophancy, i.e., alignment with user-implied beliefs evenwhen these contradict factual accuracy or rational reasoning. Prior work treats sycophancy as a surface-level artefact addressed via inference-time or post-hoc methods. We argue that it is a policy-level failure arising from missing agentic control over agreement under pressure. To make sycophancy amenable to explicit control, we propose learning agentic policies modelling LLMs’ behaviour as a decision-making problem. Our approach equips a single model with an explicit action space that includes answering directly, countering misleading signals, or asking for clarification. The policy is trained to optimise a multi-objective reward that balances task success, sycophancy resistance, and behavioural consistency via a control mechanism that operates through agentic behaviour. We evaluate the method on different benchmarks, showing that the approaches reduce sycophancy, improving performance, and generalise robustly across languages. These findings suggest that mitigating sycophancy requires moving beyond compliance-oriented generation towards agreement-agentic control.
%U https://aclanthology.org/2026.eacl-long.169/
%P 3664-3681
Markdown (Informal)
[Learning Multilingual Agentic Policy to Control Sycophancy](https://aclanthology.org/2026.eacl-long.169/) (Ranaldi & Pucci, EACL 2026)
ACL
- Leonardo Ranaldi and Giulia Pucci. 2026. Learning Multilingual Agentic Policy to Control Sycophancy. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3664–3681, Rabat, Morocco. Association for Computational Linguistics.