# CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space

arXiv: https://arxiv.org/abs/2502.12532 · HTML: https://mlsanity.com/paper/2502.12532/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 48 references that are in the map.
- First posted on arXiv 18 Feb 2025.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 25 of 25)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles](https://mlsanity.com/paper/1705.05065/) (2017)
- [ScanQA: 3D Question Answering for Spatial Scene Understanding](https://mlsanity.com/paper/2112.10482/) (2021)
- [Embodied Question Answering](https://mlsanity.com/paper/1711.11543/) (2017)
- [SQA3D: Situated Question Answering in 3D Scenes](https://mlsanity.com/paper/2210.07474/) (2022)
- [EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought](https://mlsanity.com/paper/2305.15021/) (2023)
- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI](https://mlsanity.com/paper/2407.06886/) (2024)
- [IQA: Visual Question Answering in Interactive Environments](https://mlsanity.com/paper/1712.03316/) (2017)
- [Towards Learning a Generalist Model for Embodied Navigation](https://mlsanity.com/paper/2312.02010/) (2023)
- [Language Models Meet World Models: Embodied Experiences Enhance Language Models](https://mlsanity.com/paper/2305.10626/) (2023)
- [AerialVLN: Vision-and-Language Navigation for UAVs](https://mlsanity.com/paper/2308.06735/) (2023)
- [HourVideo: 1-Hour Video-Language Understanding](https://mlsanity.com/paper/2411.04998/) (2024)
- [SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation](https://mlsanity.com/paper/2410.08189/) (2024)
- [Embodied Question Answering in Photorealistic Environments with Point Cloud Perception](https://mlsanity.com/paper/1904.03461/) (2019)
- [UrbanCLIP: Learning Text-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining from the Web](https://mlsanity.com/paper/2310.18340/) (2023)
- [Multi-Target Embodied Question Answering](https://mlsanity.com/paper/1904.04686/) (2019)
- [Explore until Confident: Efficient Exploration for Embodied Question Answering](https://mlsanity.com/paper/2403.15941/) (2024)
- [EmbodiedCity: A Benchmark Platform for Embodied Agent in Real-world City Environment](https://mlsanity.com/paper/2410.09604/) (2024)
- [ManipVQA: Injecting Robotic Affordance and Physically Grounded Information into Multi-Modal Large Language Models](https://mlsanity.com/paper/2403.11289/) (2024)
- [Perceive, Reflect, and Plan: Designing LLM Agent for Goal-Directed City Navigation without Instructions](https://mlsanity.com/paper/2408.04168/) (2024)
- [OpenGraph: Open-Vocabulary Hierarchical 3D Graph Representation in Large-Scale Outdoor Environments](https://mlsanity.com/paper/2403.09412/) (2024)
- [3D Question Answering for City Scene Understanding](https://mlsanity.com/paper/2407.17398/) (2024)
- [NoisyEQA: Benchmarking Embodied Question Answering Against Noisy Queries](https://mlsanity.com/paper/2412.10726/) (2024)

## Built on by (most cited first, 30 of 32)

- [TRAIL: Trace Reasoning and Agentic Issue Localization](https://mlsanity.com/paper/2505.08638/) (2025)
- [Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answering](https://mlsanity.com/paper/2503.11117/) (2025)
- [Explain Before You Answer: A Survey on Compositional Visual Reasoning](https://mlsanity.com/paper/2508.17298/) (2025)
- [Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?](https://mlsanity.com/paper/2602.07055/) (2026)
- [IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial Scenarios](https://mlsanity.com/paper/2505.20640/) (2025)
- [General-Purpose Aerial Intelligent Agents Empowered by Large Language Models](https://mlsanity.com/paper/2503.08302/) (2025)
- [Aerial Vision-Language Navigation with a Unified Framework for Spatial, Temporal and Embodied Reasoning](https://mlsanity.com/paper/2512.08639/) (2025)
- [USTBench: Benchmarking and Dissecting Spatiotemporal Reasoning of LLMs as Urban Agents](https://mlsanity.com/paper/2505.17572/) (2025)
- [IndustryNav: Exploring Spatial Reasoning of Embodied Agents in Dynamic Industrial Navigation](https://mlsanity.com/paper/2511.17384/) (2025)
- [Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Exploration](https://mlsanity.com/paper/2512.02458/) (2025)
- [AirVista-II: An Agentic System for Embodied UAVs Toward Dynamic Scene Semantic Understanding](https://mlsanity.com/paper/2504.09583/) (2025)
- [PhysVLM-AVR: Active Visual Reasoning for Multimodal Large Language Models in Physical Environments](https://mlsanity.com/paper/2510.21111/) (2025)
- [ReEXplore: Improving MLLMs for Embodied Exploration with Contextualized Retrospective Experience Replay](https://mlsanity.com/paper/2511.19033/) (2025)
- [Fly0: Persistent Metric Anchoring for Zero-Shot Aerial Vision-Language Navigation](https://mlsanity.com/paper/2602.15875/) (2026)
- [Domain Specific Benchmarks for Evaluating Multimodal Large Language Models](https://mlsanity.com/paper/2506.12958/) (2025)
- [Are VLMs Lost Between Sky and Space? LinkS2Bench for UAV-Satellite Dynamic Cross-View Spatial Intelligence](https://mlsanity.com/paper/2604.02020/) (2026)
- [BridgeEQA: Virtual Embodied Agents for Real Bridge Inspections](https://mlsanity.com/paper/2511.12676/) (2025)
- [Prune-Then-Plan: Step-Level Calibration for Stable Frontier Exploration in Embodied Question Answering](https://mlsanity.com/paper/2511.19768/) (2025)
- [SpatialUAV: Benchmarking Spatial Intelligence for Low-Altitude UAV Perception, Collaboration, and Motion](https://mlsanity.com/paper/2606.27876/) (2026)
- [ActiveFly-Bench: Aligning Embodied Question Answering with Vision-Language-Action for Aerial Embodied Perception](https://mlsanity.com/paper/2607.10180/) (2026)
- [Memory-Guided View Refinement for Dynamic Human-in-the-loop EQA](https://mlsanity.com/paper/2603.09541/) (2026)
- [SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes](https://mlsanity.com/paper/2605.31148/) (2026)
- [ScoutVLA: UAV-Centric Active Perception via a Dual-Expert VLA Model for Open-World Embodied Question Answering](https://mlsanity.com/paper/2606.14772/) (2026)
- [Scaffolding Foundation Models into Physical-World Agents Pushes the Frontier of Long-Horizon Navigation](https://mlsanity.com/paper/2608.30396/) (2026)
- [Towards Embodied Air-Ground Cooperative Object Search: Benchmark, Dataset and Agentic Method](https://mlsanity.com/paper/2609.08402/) (2026)
- [Towards Autonomous UAV Visual Object Search in City Space: Benchmark and Agentic Methodology](https://mlsanity.com/paper/2505.08765/) (2025)
- [UrbanWell: Benchmarking Multimodal Large Language Models for Spatio-Temporal Urban Wellbeing Analytics](https://mlsanity.com/paper/2606.15890/) (2026)
- [Lingjing: A Simulation Testbed for Multi-Agent Embodied Tasks in Open-Ended Cities](https://mlsanity.com/paper/2608.08045/) (2026)
- [Budget-Constrained Embodied Perception: Four Resource Walls and a Pre-Registered Evaluation of Access-Structured Perception on Open Models at less than 31B](https://mlsanity.com/paper/2608.22975/) (2026)
- [CityToolVQA: Tool-Augmented Visual Question Answering for 3D Spatial Cognition in Urban Low-Altitude Environments](https://mlsanity.com/paper/2609.32427/) (2026)

## Abstract (arXiv)

Embodied Question Answering (EQA) has primarily focused on indoor environments, leaving the complexities of urban settings-spanning environment, action, and perception-largely unexplored. To bridge this gap, we introduce CityEQA, a new task where an embodied agent answers open-vocabulary questions through active exploration in dynamic city spaces. To support this task, we present CityEQA-EC, the first benchmark dataset featuring 1,412 human-annotated tasks across six categories, grounded in a realistic 3D urban simulator. Moreover, we propose Planner-Manager-Actor (PMA), a novel agent tailored for CityEQA. PMA enables long-horizon planning and hierarchical task execution: the Planner breaks down the question answering into sub-tasks, the Manager maintains an object-centric cognitive map for spatial reasoning during the process control, and the specialized Actors handle navigation, exploration, and collection sub-tasks. Experiments demonstrate that PMA achieves 60.7% of human-level answering accuracy, significantly outperforming competitive baselines. While promising, the performance gap compared to humans highlights the need for enhanced visual reasoning in CityEQA. This work paves the way for future advancements in urban spatial intelligence. Dataset and code are available at https://github.com/BiluYong/CityEQA.git.