# RoboFind: Multi-Agent Personalized Object Search for People Who Are Blind or Have Low Vision arXiv: https://arxiv.org/abs/2609.20330 ยท HTML: https://mlsanity.com/paper/2609.20330/ ## Key facts - No citing papers in the map yet (data through 14 Oct 2026). - Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. - Builds on 31 of its 42 references that are in the map. - First posted on arXiv 17 Sep 2026. ## Placed in - LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/) ## Builds on (most cited first, 30 of 31) - [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023) - [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023) - [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022) - [ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects](https://mlsanity.com/paper/2006.13171/) (2020) - [Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks](https://mlsanity.com/paper/2412.06224/) (2024) - [Sim-to-Real Transfer for Vision-and-Language Navigation](https://mlsanity.com/paper/2011.03807/) (2020) - [HM3D-OVON: A Dataset and Benchmark for Open-Vocabulary Object Goal Navigation](https://mlsanity.com/paper/2409.14296/) (2024) - [LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents](https://mlsanity.com/paper/2503.10200/) (2025) - [RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints](https://mlsanity.com/paper/2503.16408/) (2025) - [WorldScribe: Towards Context-Aware Live Visual Descriptions](https://mlsanity.com/paper/2408.06627/) (2024) - [Investigating Use Cases of AI-Powered Scene Description Applications for Blind and Low Vision People](https://mlsanity.com/paper/2403.15604/) (2024) - [VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning](https://mlsanity.com/paper/2506.09049/) (2025) - [Misfitting With AI: How Blind People Verify and Contest AI Errors](https://mlsanity.com/paper/2408.06546/) (2024) - [Personalized Instance-based Navigation Toward User-Specific Objects in Realistic Environments](https://mlsanity.com/paper/2410.18195/) (2024) - [MICA: Multi-Agent Industrial Coordination Assistant](https://mlsanity.com/paper/2509.15237/) (2025) - [System Configuration and Navigation of a Guide Dog Robot: Toward Animal Guide Dog-Level Guiding Work](https://mlsanity.com/paper/2210.13368/) (2022) - [ProgramAlly: Creating Custom Visual Access Programs via Multi-Modal End-User Programming](https://mlsanity.com/paper/2408.10499/) (2024) - [Beyond Omakase: Designing Shared Control for Navigation Robots with Blind People](https://mlsanity.com/paper/2503.21997/) (2025) - [ComBodied Agents: a New Paradigm of Human-Centric Agentic AI](https://mlsanity.com/paper/2608.10915/) (2026) - [GuideNav: User-Informed Development of a Vision-Only Robotic Navigation Assistant For Blind Travelers](https://mlsanity.com/paper/2512.06147/) (2025) - [Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models](https://mlsanity.com/paper/2605.18431/) (2026) - [ShelfHelp: Empowering Humans to Perform Vision-Independent Manipulation Tasks with a Socially Assistive Robotic Cane](https://mlsanity.com/paper/2405.20501/) (2024) - [Understanding Expectations for a Robotic Guide Dog for Visually Impaired People](https://mlsanity.com/paper/2501.04594/) (2025) - [Uni-LaViRA: Language-Vision-Robot Actions Translation for Unified Embodied Navigation](https://mlsanity.com/paper/2605.27582/) (2026) - [GuideTWSI: A Diverse Tactile Walking Surface Indicator Dataset from Synthetic and Real-World Images for Blind and Low-Vision Navigation](https://mlsanity.com/paper/2603.07060/) (2026) - [From Woofs to Words: Towards Intelligent Robotic Guide Dogs with Verbal Communication](https://mlsanity.com/paper/2603.12574/) (2026) - [DogSurf: Quadruped Robot Capable of GRU-based Surface Recognition for Blind Person Navigation](https://mlsanity.com/paper/2402.03156/) (2024) - [Not an Obstacle for Dog, but a Hazard for Human: A Co-Ego Navigation System for Guide Dog Robots](https://mlsanity.com/paper/2603.20121/) (2026) - [MAR3: Multi-Agent Recognition, Reasoning, and Reflection for Reference Audio-Visual Segmentation](https://mlsanity.com/paper/2603.27706/) (2026) - [CANINE: Coaching Visually Impaired Users for Interactive Navigation with a Robot Guide Dog](https://mlsanity.com/paper/2605.19501/) (2026) ## Abstract (arXiv) Blind and low-vision users often need to locate a specific personal object rather than an arbitrary instance of the same category. The task calls for a robot that can move through the space and reach viewpoints the user cannot, and for an accessible interface where the user says which object is meant and learns whether the right one was found. We present RoboFind, a multi-agent framework in which a smartphone teaches the target and a quadruped robot carries out the search. A Target Teaching Agent converts guided smartphone recordings into a semantic target profile and a reusable multi-view reference bank through an accessible capture flow with AR guidance, speech and haptic feedback, and screen-reader support, so later missions refer to a stored object without repeating the teaching process. At runtime, a Navigation Agent explores the environment and proposes candidate targets, a Verification Agent checks each candidate against the stored references, and a Coordination and Recovery Agent completes the mission or triggers recovery and continued search. Across 32 real-robot missions, RoboFind reaches 85.0% success against 25.0% for a reconstructed sequential first-stop baseline over 20 trials with ten targets, and reduces false success from 75.0% to 5.0%. On six shared targets it succeeds in 10/12 trials, against 5/12 for 12 independently executed GPT-6 Astra-only trials. These results show that the multi-agent design fits the demands of personalized object search, where verifying object identity before declaring completion is what makes the outcome something a user can rely on.