Saved in:
| Main Authors: | , , , , |
|---|---|
| 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 |