# MulRobBench: A Decision-Level Benchmark for Safe and Security-Policy-Compliant Multimodal UAV Agents

arXiv: https://arxiv.org/abs/2607.23870 · HTML: https://mlsanity.com/paper/2607.23870/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 53 references that are in the map.
- First posted on arXiv 26 Jul 2026.

## Builds on (most cited first, 30 of 33)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models](https://mlsanity.com/paper/2306.11698/) (2023)
- [SelectiveNet: A Deep Neural Network with an Integrated Reject Option](https://mlsanity.com/paper/1901.09192/) (2019)
- [A Survey on Vision-Language-Action Models for Embodied AI](https://mlsanity.com/paper/2405.14093/) (2024)
- [MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe](https://mlsanity.com/paper/2509.18154/) (2025)
- [Building and better understanding vision-language models: insights and future directions](https://mlsanity.com/paper/2408.12637/) (2024)
- [AerialVLN: Vision-and-Language Navigation for UAVs](https://mlsanity.com/paper/2308.06735/) (2023)
- [CityNav: A Large-Scale Dataset for Real-World Aerial Navigation](https://mlsanity.com/paper/2406.14240/) (2024)
- [EmbodiedCity: A Benchmark Platform for Embodied Agent in Real-world City Environment](https://mlsanity.com/paper/2410.09604/) (2024)
- [UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban Spaces](https://mlsanity.com/paper/2503.06157/) (2025)
- [Aya Vision: Advancing the Frontier of Multilingual Multimodality](https://mlsanity.com/paper/2505.08751/) (2025)
- [UAV-ON: A Benchmark for Open-World Object Goal Navigation with Aerial Agents](https://mlsanity.com/paper/2508.00288/) (2025)
- [CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global Memory](https://mlsanity.com/paper/2505.05622/) (2025)
- [UAVScenes: A Multi-Modal Dataset for UAVs](https://mlsanity.com/paper/2507.22412/) (2025)
- [AirCopBench: A Benchmark for Multi-drone Collaborative Embodied Perception and Reasoning](https://mlsanity.com/paper/2511.11025/) (2025)
- [Cyber-Physical Systems Security -- A Survey](https://mlsanity.com/paper/1701.04525/) (2017)
- [UAVBench: An Open Benchmark Dataset for Autonomous and Agentic AI UAV Systems via LLM-Generated Flight Scenarios](https://mlsanity.com/paper/2511.11252/) (2025)
- [Vision-based Learning for Drones: A Survey](https://mlsanity.com/paper/2312.05019/) (2023)
- [MM-UAVBench: How Well Do Multimodal Large Language Models See, Think, and Plan in Low-Altitude UAV Scenarios?](https://mlsanity.com/paper/2512.23219/) (2025)

## Abstract (arXiv)

In IoT-enabled smart-city settings, Uncrewed Aerial Vehicles (UAVs) are evolving from passive sensing platforms into cyber-physical decision makers that must respect operational rules under degraded observations and ambiguous language. Existing UAV and multimodal benchmarks cover aerial perception, navigation, collaboration, and task reasoning, but rarely test whether physical evidence, protocol constraints, and action risk stay coupled at critical decisions. We introduce MulRobBench, an offline, protocol-conditioned benchmark for Vision-Language-Action (VLA) UAV agents that links real UAV multimodal observations, protocol-level security-policy constraints, and action-level cyber-physical safety within an auditable decision contract. The evaluation set contains 3,024 samples spanning 17 task-taxonomy nodes and 12 metric scoring dimensions, organized around context understanding, multimodal evidence arbitration, degradation-aware reasoning, and risk-aware action planning. MulRobBench reports controlled semantic scores alongside strict structural diagnostics for policy compliance, formatting, unsafe actions, parsing, and dimension-level validity. Across 17 uniformly audited models, the best semantic protocol-decision score reaches 0.5141 and the best strict mean scoring-dimension accuracy reaches 0.1599. A matched 20-anchor modality-removal study changes 4-15 action selections per model, showing both visual and textual inputs influence decisions while the strongest input condition varies across metrics. Per-dimension and conditional analyses identify modality-trust selection, constraint extraction, strong glare, missing data, and high-entropy operator shorthand as principal sources of action instability. The central challenge is thus stable coupling of degraded evidence, security-policy constraints, and risk-bearing action, not isolated scene recognition.