# Beyond Scene Description: Multi-Agent Orchestration for Non-visual Access to Virtual Worlds

arXiv: https://arxiv.org/abs/2609.14512 · HTML: https://mlsanity.com/paper/2609.14512/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 29 references that are in the map.
- First posted on arXiv 13 Sep 2026.

## Builds on (most cited first, 4 of 4)

- [VizWiz Grand Challenge: Answering Visual Questions from Blind People](https://mlsanity.com/paper/1802.08218/) (2018)
- [Toward Trustworthy Agentic AI: A Multimodal Framework for Preventing Prompt Injection Attacks](https://mlsanity.com/paper/2512.23557/) (2025)
- [FinAgent: An Agentic AI Framework Integrating Personal Finance and Nutrition Planning](https://mlsanity.com/paper/2512.20991/) (2025)
- [LLM-Guided Agentic Floor Plan Parsing for Accessible Indoor Navigation of Blind and Low-Vision People](https://mlsanity.com/paper/2604.23970/) (2026)

## Abstract (arXiv)

Virtual worlds now host classrooms, meetings, conferences, shops, and social venues, and nearly every interaction they expose assumes a user who can scan a three-dimensional scene, follow avatars, and read floating panels. Blind and visually impaired (BVI) users are left with assistive tools that each solve one task in isolation: naming an object, reading text, describing a scene, or planning a route. A live virtual room defeats that model: obstacles, speakers, gestures, chat, slides, and notifications arrive together, and a tool that narrates all of them trades a visual barrier for an auditory one. This paper presents MetaBlind, an architecture that distributes nonvisual access across eight specialized agents, spanning perception, navigation, social and object interaction, communication, safety and trust, memory, and personalization, and that places an Accessibility Orchestrator between those agents and the user. Agents publish candidate information into a shared accessibility context instead of speaking to the user directly. The orchestrator scores each candidate on safety relevance, goal relevance, urgency, confidence, user relevance, and estimated listening load, then releases only the items it judges relevant at that moment through speech, structured audio, or haptic output. We give the selection step a formal statement, specify the orchestration cycle as an algorithm, and define an evaluation protocol against a single-agent assistant. MetaBlind is reported at the design stage, with no prototype measurement or user study, and the protocol states which outcomes would support the design and which would refute it.