# EmbodiedLGR: Integrating Lightweight Graph Representation and Retrieval for Semantic-Spatial Memory in Robotic Agents Source: [EmbodiedLGR: Integrating Lightweight Graph Representation and Retrieval for Semantic-Spatial Memory in Robotic Agents]() Collection index: [llms.txt]() Data updated: 2026-04-22T05:23:53.567Z Authors: Paolo Riva, Leonardo Gargani, Matteo Frosi, Matteo Matteucci Published: 2026-04-20T13:45:54.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Embodied Question Answering on NaVQA](): Embodied Question Answering; NaVQA; Response Latency (s): 9.97. - [Navigation Visual Question Answering on NaVQA](): Navigation Visual Question Answering; NaVQA; Positional Accuracy: 29.17. ## Original sources and implementation [Original paper]() [PDF]()