Embodied QA

QA: Question Answering

Embodied question answering asks agents to answer questions about environments they observe and move through, often using robots or egocentric video. Common approaches combine vision-language models with active exploration, spatial maps or scene graphs, and episodic or long-term memory to find and retain relevant evidence. Benchmarks such as OpenEQA, HM-EQA, and SQA3D test scene understanding, spatial reasoning, and navigation-linked answering, while newer evaluations include dynamic, long-horizon, and multi-agent settings. A central challenge is maintaining accurate, query-relevant evidence over time: models still struggle with spatial and temporal reasoning, and stronger memory or exploration must be balanced against inference and navigation costs.

Latest papers

39 papers3 papers in the last four weeks, down 57% on the four weeks before. 0.0% of all new papers.

EmbodiedLGR: Integrating Lightweight Graph Representation and Retrieval for Semantic-Spatial Memory in Robotic Agents
Apr 20, 2026Paolo Riva, Leonardo Gargani, Matteo Frosi +1Graph Retrieval-Augmented Generation Embodied QA
Department of Electronics, Information, and Bioengineering (DEIB), Politecnico di Milano, Milan, Italy
Memory Centric Power Allocation for Multi-Agent Embodied Question Answering
Apr 20, 2026Chengyang Li, Shuai Wang, Kejiang Ye +5Embodied QA Wireless Resource Allocation
Department of Electrical and Computer Engineering, The University of Hong Kong, Hong Kong · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China · Southern University of Science and Technology, Shenzhen, China +2
See, Remember, Explore: A Benchmark and Baselines for Streaming Spatial Reasoning
Mar 25, 2026Yuxi Wei, Wei Huang, Qirui Chen +2Spatial Reasoning Benchmarks Visual Spatial Reasoning
The University of Hong Kong · Shanghai Jiao Tong University · Yinwang Intelligent Technology Co. Ltd.
GSMem: 3D Gaussian Splatting as Persistent Spatial Memory for Zero-Shot Embodied Exploration and Reasoning
Mar 19, 2026Yiren Lu, Yi Du, Disheng Liu +3Long-Term Memory for Embodied Agents Embodied AI
Case Western Reserve University · Spatial AI & Robotics (SAIR) Lab, University at Buffalo
MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents
Mar 10, 2026Kangsan Kim, Yanlai Yang, Suji Kim +4Egocentric Video QA Embodied QA
KAIST · New York University · Samsung Electronics +1
Memory-Guided View Refinement for Dynamic Human-in-the-loop EQA
Mar 10, 2026Xin Lu, Rui Li, Xun Huang +6Embodied QA Memory-Augmented Agents
University of Chinese Academy of Sciences, China · Zhongguancun Academy, China · Beihang University, China +2
FocusGraph: Graph-Structured Frame Selection for Embodied Long Video Question Answering
Mar 4, 2026Tatiana Zemskova, Solomon Andryushenko, Ilya Obrubov +4Efficient VLM Inference Egocentric Video QA
AXXX · MIRAI · Yandex +1
FAST-EQA: Efficient Embodied Question Answering with Global and Local Region Relevancy
Feb 17, 2026Haochen Zhang, Nirav Savaliya, Faizan Siddiqui +1Embodied QA Embodied Navigation
Carnegie Mellon University, USA · Honda Research Institute USA
HIMM: Human-Inspired Long-Term Memory Modeling for Embodied Exploration and Question Answering
Feb 17, 2026Ji Li, Bo Wang, Jing Xia +2Long-Term Memory for Embodied Agents Memory-Augmented Agents
The University of Hong Kong, Hong Kong SAR. · Beijing Institute of Technology, Beijing, China.

Apr 20, 2026J/K move · Enter open · S save

EmbodiedLGR: Integrating Lightweight Graph Representation and Retrieval for Semantic-Spatial Memory in Robotic Agents

Paolo Riva, Leonardo Gargani, Matteo Frosi, Matteo Matteucci

Department of Electronics, Information, and Bioengineering (DEIB), Politecnico di Milano, Milan, Italy

Graph Retrieval-Augmented Generation Embodied QA Robotics Graph-Based Agent Memory Robotic Spatial Memory Memory-Augmented Language Model Agents

Open paper AskPDF arXiv

As the world of agentic artificial intelligence applied to robotics evolves, the need for agents capable of building and retrieving memories and observations efficiently is increasing. Robots operating in complex environments must build memory structures to enable useful human-robot interactions by leveraging the mnemonic representation of the current operating context. People interacting with robots may expect the embodied agent to provide information about locations, events, or objects, which requires the agent to provide precise answers within human-like inference times to be perceived as responsive. We propose the Embodied Light Graph Retrieval Agent (EmbodiedLGR-Agent), a visual-language model (VLM)-driven agent architecture that constructs dense and efficient representations of robot operating environments. EmbodiedLGR-Agent directly addresses the need for an efficient memory representation of the environment by providing a hybrid building-retrieval approach built on parameter-efficient VLMs that store low-level information about objects and their positions in a semantic graph, while retaining high-level descriptions of the observed scenes with a traditional retrieval-augmented architecture. EmbodiedLGR-Agent is evaluated on the popular NaVQA dataset, achieving state-of-the-art performance in inference and querying times for embodied agents, while retaining competitive accuracy on the global task relative to the current state-of-the-art approaches. Moreover, EmbodiedLGR-Agent was successfully deployed on a physical robot, showing practical utility in real-world contexts through human-robot interaction, while running the visual-language model and the building-retrieval pipeline locally.