# Guide Me Out: A Framework to Benchmark VLM Operators Communication in Crisis Scenarios

arXiv: https://arxiv.org/abs/2606.09428 · HTML: https://mlsanity.com/paper/2606.09428/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 28 references that are in the map.
- First posted on arXiv 8 Jun 2026.

## Builds on (most cited first, 11 of 11)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [Twitter as a Lifeline: Human-annotated Twitter Corpora for NLP of Crisis-related Messages](https://mlsanity.com/paper/1605.05894/) (2016)
- [Talk the Walk: Navigating New York City through Grounded Dialogue](https://mlsanity.com/paper/1807.03367/) (2018)
- [CrisisBERT: a Robust Transformer for Crisis Classification and Contextual Crisis Embedding](https://mlsanity.com/paper/2005.06627/) (2020)
- [CrisisSense-LLM: Instruction Fine-Tuned Large Language Model for Multi-label Social Media Text Classification in Disaster Informatics](https://mlsanity.com/paper/2406.15477/) (2024)
- [LLM-Assisted Crisis Management: Building Advanced LLM Platforms for Effective Emergency Response and Public Collaboration](https://mlsanity.com/paper/2402.10908/) (2024)
- [TagaVLM: Topology-Aware Global Action Reasoning for Vision-Language Navigation](https://mlsanity.com/paper/2603.02972/) (2026)
- [GROKE: Vision-Free Navigation Instruction Evaluation via Graph Reasoning on OpenStreetMap](https://mlsanity.com/paper/2601.07375/) (2026)

## Abstract (arXiv)

Effective crisis response requires spatially grounded communication that bridges linguistic guidance of civilians with the physical environment, accounting for structural bottlenecks, evolving threats, and agent-specific contexts. Yet, current NLP research in crisis communication remains mainly limited to static, text-only classification settings, overlooking the critical communicative role of AI operators in dynamic, embodied scenarios. We address this gap with a novel benchmarking framework for evaluating Vision-Language Models (VLMs) tasked with guiding civilian agents through simulated evacuations. We test two communication strategies (narrowcast vs. broadcast), two environment representations (visual vs. graph-based), and two threat behaviors (static vs. moving) across nine maps of varying structural complexity. Our results show that Narrowcast consistently reduces civilian Fail rates compared to Broadcast across all difficulty levels. Guidance quality depends heavily on how the VLM operator represents the world: the visual modality drives performance, while adding an adjacency graph is model-dependent and often harmful. Moving threats raise Fail rates across all conditions as communication must continuously adapt over time. Together, these findings show that deploying VLMs as AI operators in evacuation scenarios remains a non-trivial challenge, where the choice of communication strategy and input representation can directly determine the success or failure of the intervention.