[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82483-en":3,"doc-seo-82483-105":29,"detail-sidebar-cat-0-en-105":95},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},82483,1099513958762,"Logic","https://ap-avatar.wpscdn.com/avatar/1000023916a998db790?x-image-process=image/resize,m_fixed,w_180,h_180&k=1782109480056885918",8,"Research & Report","EgoSafetyBench: A Diagnostic Egocentric Video Benchmark for Evaluating Embodied VLMs as Runtime Safety Guards","Vision-language models (VLMs) are proposed as runtime safety guards for embodied agents, where reliable monitoring must distinguish genuinely unsafe moments from routine yet superficially alarming activity. EgoSafetyBench introduces a diagnostic egocentric video benchmark with 1,200 robotview scenarios, annotated every half-second. Two tracks evaluate streaming guard behavior: situational hazards and visual-channel text mismatches. Contrastive ladders isolate single deciding cues to measure true physical-safety reasoning. Experiments on ten VLMs show hazard video recognition yet systematic failures on contextual hazards, and misleading in-scene signs harm both accuracy and intervention calibration.","EgoSafetyBench: A Diagnostic Egocentric Video Benchmark for Evaluating Embodied VLMs as Runtime Safety Guards  \narXiv :2607 .00218v1 [ cs .CV] 30 Jun 2026  \nSiddhant Panpatil 1 * Arth Singh 1∗ Mijin Koo 1 ,2 Chaeyun Kim 1 ,2 Haon Park1 ,2 Dasol Choi 1†  \n1AIM Intelligence 2 Seoul National University  \n{sid, arth, mijinkoo, chaeyun, haon, [dasol.choi](dasol.choi}@aim-intelligence.com)[}](dasol.choi}@aim-intelligence.com)[@aim-intelligence.com](dasol.choi}@aim-intelligence.com)  \n HuggingFace  GitHub  \nAbstract  \nVision-language models (VLMs) are now proposed as runtime safety guards for embodied agents in homes and factories. A deployable guard must catch genuinely unsafe situations while avoiding unnecessary intervention on routine but superficially alarming activity, a distinction that binary safety benchmarks obscure. We introduce EGOSAFETYBENCH, an egocentric video benchmark of 1,200 robotview scenarios annotated at half-second granularity, to evaluate VLMs as streaming guards across two tracks. The situational track (800 scenarios) spans four families, from routine and safe-but-suspicious scenes to obvious and contextual hazards. The visual-channel track (400 scenarios) targets in-scene text—a sign, sticker, or label visible in the scene—that can misrepresent the physical situation, pairing each misleading sign with a truthful version to test both whether a guard flags the text as misleading and whether the text corrupts its physical-safety judgment. Both tracks use contrastive ladders: near-identical scenarios differing only in a single visible deciding cue, so a correct call must hinge on that cue rather than the overall scene type. We evaluate ten open- and closed-source VLMs. We find that while guards reliably recognize videos containing hazards, they often miss specific hazardous moments, particularly contextual hazards. Furthermore, misleading inscene signs degrade all tested guards: vulnerable models miss up to a third of hazards, while robust models overintervene on safe content. Matched controls reveal that apparent safety robustness often reflects indiscriminate alarming rather than true physical reasoning.  \n*Equal contribution.†Corresponding author.  \n1. Introduction  \nEmbodied agents powered by vision-language models (VLMs) [8, 16, 29] are increasingly deployed in humancentric environments [25] . This highlights the need for runtime safety guards [5, 15] that monitor the robot’s egocentric stream and interrupt unsafe behavior before harm occurs. Such a guard faces two competing requirements: it must detect genuinely unsafe situations, including context-dependent risks, while allowing routine activity that is inherently benign despite alarming surface features. For instance, a kitchen knife is not inherently dangerous; safety depends entirely on the dynamic relation between the robot’s action and the scene context. However, most embodied-safety benchmarks [9, 18, 20, 23, 27] collapse this nuanced problem into binary safe/unsafe classification. This conflates two distinct failures: over-flagging safe scenes, and missing contextual hazards. Consequently, binary evaluation cannot distinguish whether a model is a reliable runtime guard or merely a surface-cue detector.  \nTo expose these distinctions, we introduce EGOSAFETYBENCH, an egocentric video benchmark evaluated chunkby-chunk in an online, future-blind setting that approximates a streaming guard. Each scenario is rendered from a humanoid robot’s first-person perspective and annotated at half-second granularity. Our annotation framework decouples evaluation along two independent axes (Figure 1) . The first is a situational four-family taxonomy, from plainly safe (S1) and resolved-confound safe (S2) to obvious (U1) and contextual (U2) hazards. The second is a visual-channel mismatch (VCM) axis, marking whether an in-scene channel (a sign, sticker, or screen) misrepresents the situation [4, 28] . Importantly, every misleading channel is paired with a truthful co","cbCaioTdslAP7qTI","https://ap.wps.com/l/cbCaioTdslAP7qTI","pdf",3046602,1,14,"English","en",105,"# Abstract\n# Introduction\n## Runtime safety guards for embodied agents\n## Limitations of binary safety benchmarks\n## EGOSAFETYBENCH design and annotation axes\n## Contrastive ladder methodology\n## Evaluation setup and findings","[{\"question\":\"What problem does EgoSafetyBench address for embodied VLMs in runtime safety?\",\"answer\":\"It addresses the need for a guard that catches genuinely unsafe situations while not over-intervening on routine activity that only looks alarming on the surface.\"},{\"question\":\"How does EGOSAFETYBENCH structure the benchmark cases?\",\"answer\":\"It provides 1,200 egocentric robotview scenarios annotated at half-second granularity, split into a situational track (800) and a visual-channel text track (400).\"},{\"question\":\"What is the purpose of the contrastive ladder design?\",\"answer\":\"Scenarios differ only by a single visible deciding cue, forcing correct predictions to rely on the safety-relevant relationship rather than general scene correlations.\"},{\"question\":\"What key evaluation trends are reported for tested VLMs?\",\"answer\":\"Models often detect videos containing hazards but frequently miss specific hazardous moments, especially contextual hazards; misleading in-scene signs also degrade performance and can trigger over-intervention.\"}]",1784180843,35,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":90,"head_meta":92,"extra_data":94,"updated_unix":27},"egosafetybench-a-diagnostic-egocentric-video-benchmark-for-evaluating-embodied-vlms-as-runtime-safety-guards","",{"@graph":35,"@context":89},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/egosafetybench-a-diagnostic-egocentric-video-benchmark-for-evaluating-embodied-vlms-as-runtime-safety-guards/82483/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does EgoSafetyBench address for embodied VLMs in runtime safety?","Question",{"text":75,"@type":76},"It addresses the need for a guard that catches genuinely unsafe situations while not over-intervening on routine activity that only looks alarming on the surface.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does EGOSAFETYBENCH structure the benchmark cases?",{"text":80,"@type":76},"It provides 1,200 egocentric robotview scenarios annotated at half-second granularity, split into a situational track (800) and a visual-channel text track (400).",{"name":82,"@type":73,"acceptedAnswer":83},"What is the purpose of the contrastive ladder design?",{"text":84,"@type":76},"Scenarios differ only by a single visible deciding cue, forcing correct predictions to rely on the safety-relevant relationship rather than general scene correlations.",{"name":86,"@type":73,"acceptedAnswer":87},"What key evaluation trends are reported for tested VLMs?",{"text":88,"@type":76},"Models often detect videos containing hazards but frequently miss specific hazardous moments, especially contextual hazards; misleading in-scene signs also degrade performance and can trigger over-intervention.","https://schema.org",{"og:url":51,"og:type":91,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":93,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":45,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":136,"slug":138},10,"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":45,"category_name":141,"show_sort_weight":110,"slug":142},19,"General","general"]