mlsanityData to 14 Oct 2026

IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial Scenarios

arXiv 2505.20640 ↗First posted 27 May 2025cs.CVcited by 13

On the map: LLM reasoning → Spatial and embodied reasoning

Abstract (arXiv)

Existing Embodied Question Answering (EQA) benchmarks primarily focus on household environments, often overlooking safety-critical aspects and reasoning processes pertinent to industrial settings. This drawback limits the evaluation of agent readiness for real-world industrial applications. To bridge this, we introduce IndustryEQA, the first benchmark dedicated to evaluating embodied agent capabilities within safety-critical warehouse scenarios. Built upon the NVIDIA Isaac Sim platform, IndustryEQA provides high-fidelity episodic memory videos featuring diverse industrial assets, dynamic human agents, and carefully designed hazardous situations inspired by real-world safety guidelines. The benchmark includes rich annotations covering six categories: equipment safety, human safety, object recognition, attribute recognition, temporal understanding, and spatial understanding. Besides, it also provides extra reasoning evaluation based on these categories. Specifically, it comprises 971 question-answer pairs generated from small warehouse and 373 pairs from large ones, incorporating scenarios with and without human. We further propose a comprehensive evaluation framework, including various baseline models, to assess their general perception and reasoning abilities in industrial environments. IndustryEQA aims to steer EQA research towards developing more robust, safety-aware, and practically applicable embodied agents for complex industrial environments. Benchmark and codes are available.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 31 of its 43 references that are in the map. First posted on arXiv 27 May 2025.

Builds on

31 of 43 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022SQA3D: Situated Question Answering in 3D Scenes14 Oct

Other references · 30

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2025Qwen2.5-VL Technical Reportcited by 5,587
  5. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,599
  6. 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
  7. 2023Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotationscited by 928
  8. 2023RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedbackcited by 625
  9. 2021Habitat 2.0: Training Home Assistants to Rearrange their Habitatcited by 511
  10. 2024Improve Mathematical Reasoning in Language Models by Automated Process Supervisioncited by 441
  11. 2021ScanQA: 3D Question Answering for Spatial Scene Understandingcited by 346
  12. 2017Embodied Question Answeringcited by 336
18 more
  1. 2022Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activitiescited by 287
  2. 2025Unified Reward Model for Multimodal Understanding and Generationcited by 199
  3. 2017IQA: Visual Question Answering in Interactive Environmentscited by 155
  4. 2024LLaVA-Critic: Learning to Evaluate Multimodal Modelscited by 134
  5. 2018Building Generalizable Agents with a Realistic and Rich 3D Environmentcited by 109
  6. 2019Embodied Question Answering in Photorealistic Environments with Point Cloud Perceptioncited by 103
  7. 2024ARGS: Alignment as Reward-Guided Searchcited by 103
  8. 2025Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuningcited by 90
  9. 2019Multi-Target Embodied Question Answeringcited by 74
  10. 2024LiFT: Leveraging Human Feedback for Text-to-Video Model Alignmentcited by 53
  11. 2023Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answeringcited by 41
  12. 2025Visual Large Language Models for Generalized and Specialized Applicationscited by 36
  13. 2025CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Spacecited by 32
  14. 2021Knowledge-based Embodied Question Answeringcited by 29
  15. 2024Boosting Audio Visual Question Answering via Key Semantic-Aware Cuescited by 14
  16. 2025FaultGPT: Industrial Fault Diagnosis Question Answering System by Vision Language Modelscited by 4
  17. 2024QA-TOOLBOX: Conversational Question-Answering for process task guidance in manufacturingcited by 2
  18. 2024Coal Mining Question Answering with LLMscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 9.

13 papers.

Sort:

By area:

Similar, not cited

Close in wording, no citation either way

  1. 2025Multi-Step Reasoning for Embodied Question Answering via Tool Augmentation
  2. 2026Extending Embodied Question Answering from Perception to Decision
  3. 2026ERQA-Plus: A Diagnostic Benchmark for Reasoning in Embodied AI
  4. 2025StreamEQA: Towards Streaming Video Understanding for Embodied Scenarios
  5. 2024EfficientEQA: An Efficient Approach to Open-Vocabulary Embodied Question Answering
  6. 2024NoisyEQA: Benchmarking Embodied Question Answering Against Noisy Queries
  7. 2026SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models
  8. 2024GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering