Saved in:
Bibliographic Details
Main Authors: Ali, Muhammad Qasim, Nair, Saeejith, Wong, Alexander, Cui, Yuchen, Chen, Yuhao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.01174
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909632216170496
author Ali, Muhammad Qasim
Nair, Saeejith
Wong, Alexander
Cui, Yuchen
Chen, Yuhao
author_facet Ali, Muhammad Qasim
Nair, Saeejith
Wong, Alexander
Cui, Yuchen
Chen, Yuhao
contents Structured scene representations are a core component of embodied agents, helping to consolidate raw sensory streams into readable, modular, and searchable formats. Due to their high computational overhead, many approaches build such representations in advance of the task. However, when the task specifications change, such static approaches become inadequate as they may miss key objects, spatial relations, and details. We introduce GraphPad, a modifiable structured memory that an agent can tailor to the needs of the task through API calls. It comprises a mutable scene graph representing the environment, a navigation log indexing frame-by-frame content, and a scratchpad for task-specific notes. Together, GraphPad serves as a dynamic workspace that remains complete, current, and aligned with the agent's immediate understanding of the scene and its task. On the OpenEQA benchmark, GraphPad attains 55.3%, a +3.0% increase over an image-only baseline using the same vision-language model, while operating with five times fewer input frames. These results show that allowing online, language-driven refinement of 3-D memory yields more informative representations without extra training or data collection.
format Preprint
id arxiv_https___arxiv_org_abs_2506_01174
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GraphPad: Inference-Time 3D Scene Graph Updates for Embodied Question Answering
Ali, Muhammad Qasim
Nair, Saeejith
Wong, Alexander
Cui, Yuchen
Chen, Yuhao
Artificial Intelligence
Structured scene representations are a core component of embodied agents, helping to consolidate raw sensory streams into readable, modular, and searchable formats. Due to their high computational overhead, many approaches build such representations in advance of the task. However, when the task specifications change, such static approaches become inadequate as they may miss key objects, spatial relations, and details. We introduce GraphPad, a modifiable structured memory that an agent can tailor to the needs of the task through API calls. It comprises a mutable scene graph representing the environment, a navigation log indexing frame-by-frame content, and a scratchpad for task-specific notes. Together, GraphPad serves as a dynamic workspace that remains complete, current, and aligned with the agent's immediate understanding of the scene and its task. On the OpenEQA benchmark, GraphPad attains 55.3%, a +3.0% increase over an image-only baseline using the same vision-language model, while operating with five times fewer input frames. These results show that allowing online, language-driven refinement of 3-D memory yields more informative representations without extra training or data collection.
title GraphPad: Inference-Time 3D Scene Graph Updates for Embodied Question Answering
topic Artificial Intelligence
url https://arxiv.org/abs/2506.01174