SafeSceneReason: A Multimodal Reasoning Benchmark Connecting Industrial Hazards with Accident Knowledge
On the map: LLM reasoning → Reasoning for agents, planning and code
Abstract (arXiv)
Industrial-safety understanding requires more than detecting workers, equipment, and personal protective equipment. Models must also assess compliance, identify hazardous interactions, explain potential accident mechanisms, and recommend preventive actions. Existing safety datasets primarily focus on visual perception or isolated violation recognition and provide limited supervision for evidence-grounded reasoning. We introduce SafeSceneReason, a multimodal industrial-safety reasoning benchmark and companion training corpus that connects workplace scenes with knowledge from occupational accident investigations. SafeSceneReason combines two complementary data-construction pipelines. The scene-centric pipeline converts annotated workplace images into executable safety scene graphs and generates deterministic answers through program execution over objects, relations, and safety rules. The report-centric pipeline extracts figures and contextual evidence from accident reports and constructs multimodal questions using evidence graphs, explicit information boundaries, multi-step reasoning paths, and iterative verification. The resulting resource contains 110,581 verified scene-centric question--answer pairs and 13,114 refined report-centric question--answer pairs, covering perception, spatial and quantitative reasoning, compliance assessment, evidence synthesis, causal analysis, and mitigation-oriented decision making. Evaluation of representative proprietary and open-source vision--language models reveals substantial performance differences and persistent weaknesses in comparative, technical, and multi-evidence reasoning, demonstrating that strong general visual understanding does not yet guarantee reliable industrial-safety reasoning.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 9 of its 38 references that are in the map. First posted on arXiv 10 Aug 2026.
Builds on
9 of 38 references.
References · 9
- 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
- 2018YOLOv3: An Incremental Improvementcited by 2,652
- 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
- 2024MinerU: An Open-Source Solution for Precise Document Content Extractioncited by 255
- 2025Using Vision Language Models for Safety Hazard Identification in Constructioncited by 12
- 2025IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial Scenarioscited by 12
- 2025iSafetyBench: A video-language benchmark for safety in industrial environmentcited by 5
- 2026Multimodal Benchmark for Safety Assessment in Industrial Inspection Scenarioscited by 1
- 2026SteelBench: Evaluating Vision-Language Models in Real-World Industrial Environmentscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025AccidentBench: Benchmarking Multimodal Understanding and Reasoning in Vehicle Accidents and Beyond
- 2025Scene Graph-Guided Generative AI Framework for Synthesizing and Evaluating Industrial Hazard Scenarios
- 2026Toward Autonomous Laboratory Safety Monitoring with Vision Language Models: Learning to See Hazards Through Scene Structure
- 2025Towards Evaluating Proactive Risk Awareness of Multimodal Language Models
- 2026Visual Compliance via Executable Safety Rule Entailment
- 2025GuardTrace-VL: Detecting Unsafe Multimodel Reasoning via Iterative Safety Supervision
- 2026SafeBuild-Bench: A Temporal-Robust Construction Safety Benchmark with Graph-Enhanced Data Mining
- 2026LABSHIELD: A Multimodal Benchmark for Safety-Critical Reasoning and Planning in Scientific Laboratories