@inproceedings{choi-etal-2026-memory,
title = "Memory{--}Environment Dual-Grounding for Embodied Agents: Active Information Seeking Beyond Passive Observation",
author = "Choi, Jae-Woo and
Oh, Sehoon and
Kim, Ue-Hwan",
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.16/",
pages = "317--338",
ISBN = "979-8-89176-462-0",
abstract = "Recent LLM-based embodied agents have advanced in high-level task planning. Yet, they frequently suffer from hallucinations and brittle reasoning due to passive observation{---}either omitting fine-grained attributes or overwhelming the planner with irrelevant information. We propose SceneQueryPlanner, a memory-environment dual-grounded agent that integrates active information seeking into the planning loop by decomposing instructions and selectively executing environmental interactions or structured queries over a dynamic 3D scene graph to retrieve task-relevant information on demand. By treating information acquisition as a first-class planning action, our approach enables explicit verification and supports reliable long-horizon reasoning over object attributes. For rigorous evaluation, we introduce AttPlan-Bench, a benchmark of multi-room, long-horizon household tasks requiring attribute-aware reasoning. Experiments demonstrate that our dual-grounding strategy outperforms passive baselines, yielding more stable and scalable reasoning across diverse tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="choi-etal-2026-memory">
<titleInfo>
<title>Memory–Environment Dual-Grounding for Embodied Agents: Active Information Seeking Beyond Passive Observation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jae-Woo</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sehoon</namePart>
<namePart type="family">Oh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ue-Hwan</namePart>
<namePart type="family">Kim</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>Recent LLM-based embodied agents have advanced in high-level task planning. Yet, they frequently suffer from hallucinations and brittle reasoning due to passive observation—either omitting fine-grained attributes or overwhelming the planner with irrelevant information. We propose SceneQueryPlanner, a memory-environment dual-grounded agent that integrates active information seeking into the planning loop by decomposing instructions and selectively executing environmental interactions or structured queries over a dynamic 3D scene graph to retrieve task-relevant information on demand. By treating information acquisition as a first-class planning action, our approach enables explicit verification and supports reliable long-horizon reasoning over object attributes. For rigorous evaluation, we introduce AttPlan-Bench, a benchmark of multi-room, long-horizon household tasks requiring attribute-aware reasoning. Experiments demonstrate that our dual-grounding strategy outperforms passive baselines, yielding more stable and scalable reasoning across diverse tasks.</abstract>
<identifier type="citekey">choi-etal-2026-memory</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.16/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>317</start>
<end>338</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Memory–Environment Dual-Grounding for Embodied Agents: Active Information Seeking Beyond Passive Observation
%A Choi, Jae-Woo
%A Oh, Sehoon
%A Kim, Ue-Hwan
%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 choi-etal-2026-memory
%X Recent LLM-based embodied agents have advanced in high-level task planning. Yet, they frequently suffer from hallucinations and brittle reasoning due to passive observation—either omitting fine-grained attributes or overwhelming the planner with irrelevant information. We propose SceneQueryPlanner, a memory-environment dual-grounded agent that integrates active information seeking into the planning loop by decomposing instructions and selectively executing environmental interactions or structured queries over a dynamic 3D scene graph to retrieve task-relevant information on demand. By treating information acquisition as a first-class planning action, our approach enables explicit verification and supports reliable long-horizon reasoning over object attributes. For rigorous evaluation, we introduce AttPlan-Bench, a benchmark of multi-room, long-horizon household tasks requiring attribute-aware reasoning. Experiments demonstrate that our dual-grounding strategy outperforms passive baselines, yielding more stable and scalable reasoning across diverse tasks.
%U https://aclanthology.org/2026.findings-emnlp.16/
%P 317-338
Markdown (Informal)
[Memory–Environment Dual-Grounding for Embodied Agents: Active Information Seeking Beyond Passive Observation](https://aclanthology.org/2026.findings-emnlp.16/) (Choi et al., Findings 2026)
ACL