ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper Memory–Environment Dual-Grounding for Embodied Agents: Active Information Seeking Beyond Passive Observation
Cited - time in scopus Share share facebook twitter linkedin kakaostory
Authors
Jae-Woo Choi, Sehoon Oh, Ue-Hwan Kim
Issue Date
2026-10
Citation
Findings of the Association for Computational Linguistics: EMNLP 2026, pp.317-338
Publisher
Association for Computational Linguistics
Language
English
Type
Conference Paper
DOI
https://dx.doi.org/10.18653/2026.findings-emnlp.16
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.
KSP Keywords
3D scene, Fine grained(FG), First-class, Information acquisition, Irrelevant information, Scalable reasoning, Scene graph, Task planning, information seeking