@inproceedings{fu-etal-2026-beyond,
title = "Beyond Blind Following: Evaluating Robustness of {LLM} Agents under Imperfect Guidance",
author = "Fu, Yao and
Qiu, Ran and
Wang, Xinhe and
Sansom, Jacob and
Prabhu, Sathvika Ayyappa and
Tang, Huijie and
Kim, Jaekyeom and
Sohn, Sungryull and
Lee, Honglak",
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.310/",
pages = "6591--6618",
ISBN = "979-8-89176-380-7",
abstract = "Large language models (LLMs) have shown strong capabilities as task-solving agents across interactive domains. However, in complex environments, these agents may need to rely on auxiliary guidance to reduce the search space or make up for limited domain-specific knowledge. Such guidance includes human-provided manuals and demonstrations, retrieved examples from memory or external tools, high-level heuristics, and agent-acquired knowledge from prior interactions. However, this guidance may be imperfect. For example, due to changes in the environment, ambiguous or simplified language, or retrieval errors from external sources, guidance can be incomplete, outdated, or contextually mismatched, potentially causing errors or failures during task execution. To address this, we introduce MIRAGE, a benchmark for MeasurIng Robustness of LLM Agents under Imperfect GuidancE. MIRAGE includes procedurally generated environments in navigation, cooking, and gaming, where both the environment and the auxiliary guidance vary in fidelity and relevance. We further extend MIRAGE to realistic web tasks via WebArena, using noisy or underspecified instructions extracted from demonstrations. Our findings reveal critical failure modes in current LLM agents and motivate future work on improving their robustness under imperfect guidance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fu-etal-2026-beyond">
<titleInfo>
<title>Beyond Blind Following: Evaluating Robustness of LLM Agents under Imperfect Guidance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yao</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ran</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinhe</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacob</namePart>
<namePart type="family">Sansom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sathvika</namePart>
<namePart type="given">Ayyappa</namePart>
<namePart type="family">Prabhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huijie</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaekyeom</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sungryull</namePart>
<namePart type="family">Sohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Honglak</namePart>
<namePart type="family">Lee</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) have shown strong capabilities as task-solving agents across interactive domains. However, in complex environments, these agents may need to rely on auxiliary guidance to reduce the search space or make up for limited domain-specific knowledge. Such guidance includes human-provided manuals and demonstrations, retrieved examples from memory or external tools, high-level heuristics, and agent-acquired knowledge from prior interactions. However, this guidance may be imperfect. For example, due to changes in the environment, ambiguous or simplified language, or retrieval errors from external sources, guidance can be incomplete, outdated, or contextually mismatched, potentially causing errors or failures during task execution. To address this, we introduce MIRAGE, a benchmark for MeasurIng Robustness of LLM Agents under Imperfect GuidancE. MIRAGE includes procedurally generated environments in navigation, cooking, and gaming, where both the environment and the auxiliary guidance vary in fidelity and relevance. We further extend MIRAGE to realistic web tasks via WebArena, using noisy or underspecified instructions extracted from demonstrations. Our findings reveal critical failure modes in current LLM agents and motivate future work on improving their robustness under imperfect guidance.</abstract>
<identifier type="citekey">fu-etal-2026-beyond</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-long.310/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>6591</start>
<end>6618</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Blind Following: Evaluating Robustness of LLM Agents under Imperfect Guidance
%A Fu, Yao
%A Qiu, Ran
%A Wang, Xinhe
%A Sansom, Jacob
%A Prabhu, Sathvika Ayyappa
%A Tang, Huijie
%A Kim, Jaekyeom
%A Sohn, Sungryull
%A Lee, Honglak
%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 fu-etal-2026-beyond
%X Large language models (LLMs) have shown strong capabilities as task-solving agents across interactive domains. However, in complex environments, these agents may need to rely on auxiliary guidance to reduce the search space or make up for limited domain-specific knowledge. Such guidance includes human-provided manuals and demonstrations, retrieved examples from memory or external tools, high-level heuristics, and agent-acquired knowledge from prior interactions. However, this guidance may be imperfect. For example, due to changes in the environment, ambiguous or simplified language, or retrieval errors from external sources, guidance can be incomplete, outdated, or contextually mismatched, potentially causing errors or failures during task execution. To address this, we introduce MIRAGE, a benchmark for MeasurIng Robustness of LLM Agents under Imperfect GuidancE. MIRAGE includes procedurally generated environments in navigation, cooking, and gaming, where both the environment and the auxiliary guidance vary in fidelity and relevance. We further extend MIRAGE to realistic web tasks via WebArena, using noisy or underspecified instructions extracted from demonstrations. Our findings reveal critical failure modes in current LLM agents and motivate future work on improving their robustness under imperfect guidance.
%U https://aclanthology.org/2026.eacl-long.310/
%P 6591-6618
Markdown (Informal)
[Beyond Blind Following: Evaluating Robustness of LLM Agents under Imperfect Guidance](https://aclanthology.org/2026.eacl-long.310/) (Fu et al., EACL 2026)
ACL
- Yao Fu, Ran Qiu, Xinhe Wang, Jacob Sansom, Sathvika Ayyappa Prabhu, Huijie Tang, Jaekyeom Kim, Sungryull Sohn, and Honglak Lee. 2026. Beyond Blind Following: Evaluating Robustness of LLM Agents under Imperfect Guidance. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6591–6618, Rabat, Morocco. Association for Computational Linguistics.