{"article":{"annotation":{"article_id":"brazilian-researchers-benchmark-agentic-web-technology-stacks","available_at":"2026-10-12T23:33:51.424523Z","geography_revision":"ef6ee0010dda5fe7b240fd514749b43e214c57da73222d2e40ec83b276dd0977","id":"335c1f332445403fbb2c2a0fdaf788ebefd914f3ecf74372692c0279d846adec","input_sha256":"595ff1874fee47ef2d550d92c0696c4d8fe5a7454d6b8d5b075b4312d9d2a08c","limitations":["Rule-derived subjects are candidates, not verified editorial labels or calibrated model probabilities.","Coverage is distinct from event location. Unknown country/city/coordinates remain absent; no automatic geocoding.","Article geometries keep their stated precision and methodology; reproducing them is not independent coordinate verification."],"method":"controlled-rules-v1","places":[{"admin1":null,"city":null,"coordinate_note":null,"coordinate_reference_system":"OGC:CRS84","coordinate_source":null,"country":"BR","evidence":[{"field":"country","language":"en","note":"Explicit preserved editorial country/region; no city or national centroid inferred","source_urls":["https://arxiv.org/html/2610.13703v1"]}],"geometry":null,"id":"iso3166-1:BR","kind":"country-or-area","labels":{"ar":"البرازيل","en":"Brazil","es":"Brasil","fr":"Brésil"},"match_status":"candidate","precision":"regional","role":"coverage","uncertainty_m":null}],"rules_sha256":"fb5ad3c27c91cb840f7a0a05f7f64a5cb26ad0374409ff9457f277c7092e22b4","schema_version":1,"subjects":[{"concept_id":"medtop:20001298","confidence":null,"confidence_method":null,"evidence":[{"field":"en.title+en.summary","language":"en","note":"Subject suggested from the title or summary: AI","source_urls":["https://arxiv.org/html/2610.13703v1"]}],"method":"controlled-rules-v1","rule_id":"artificial-intelligence","status":"candidate"}],"taxonomy_revision":"1f2db31d811fca07e99b16d402c10e2cc2965c9df1c7b41d9be348b40a24e7fb","taxonomy_version":"IPTC Media Topics 2026-Q2"},"api_url":"https://newsverum.com/api/v1/articles/brazilian-researchers-benchmark-agentic-web-technology-stacks?lang=fr","category":"technology","content":{"key_points":[],"paragraphs":["Des chercheurs de NIC.br et de PUC-SP ont publié le 9 octobre une étude présentant MASTIF, un cadre destiné à comparer des combinaisons de technologies pour les systèmes multi-agents. L’évaluation a croisé trois modèles de langage, trois protocoles de communication et quatre cadres d’implémentation sur 300 tâches du benchmark Mind2Web.","L’article rapporte des écarts selon les mesures — taux d’achèvement, durée, concision, usage des outils et stabilité des valeurs sociales — sans qu’une seule combinaison soit la meilleure partout. Les auteurs soulignent les limites des tâches et des modèles étudiés. Ces résultats constituent un point de référence expérimental et ne garantissent pas les performances d’agents en situation réelle."],"sections":[]},"corrections":[],"country":"BR","data":{"blocks":[{"columns":[{"key":"indicator","label":{"ar":"المؤشر","de":"Indikator","en":"Indicator","es":"Indicador","fr":"Indicateur","pt":"Indicador","tr":"Gösterge"},"type":"text"},{"key":"count","label":{"ar":"العدد في نطاق التجربة","de":"Zahl im Versuchsrahmen","en":"Experimental scope count","es":"Cantidad en el alcance experimental","fr":"Nombre dans le périmètre expérimental","pt":"Quantidade no escopo experimental","tr":"Deney kapsamındaki sayı"},"type":"number","unit":"count"},{"key":"released","label":{"ar":"تاريخ نشر المسودة الأولية","de":"Veröffentlichungsdatum des Preprints","en":"Preprint publication date","es":"Fecha de publicación de la prepublicación","fr":"Date de publication de la prépublication","pt":"Data de publicação da pré-publicação","tr":"Ön baskının yayın tarihi"},"type":"date"}],"description":{"ar":"300 مهمة من Mind2Web؛ عينة تجربة MASTIF","de":"300 Mind2Web-Aufgaben; MASTIF-Versuchsstichprobe","en":"300 Mind2Web tasks; MASTIF experiment sample","es":"300 tareas de Mind2Web; muestra experimental de MASTIF","fr":"300 tâches Mind2Web ; échantillon de l’expérience MASTIF","pt":"300 tarefas do Mind2Web; amostra experimental do MASTIF","tr":"300 Mind2Web görevi; MASTIF deney örneklemi"},"id":"study-experimental-scope","methodology":{"ar":"العدد الذي أوردته الورقة لنطاق التجربة؛ وليس إحصاءً وطنياً أو نتيجة ميدانية.","de":"Die Zahl bezeichnet den im Artikel genannten Versuchsrahmen; keine nationale Statistik oder Feldmessung.","en":"Count reported by the paper for its experimental scope; not a national statistic or field result.","es":"Cifra del alcance experimental indicado en el artículo; no es una estadística nacional ni un resultado de campo.","fr":"Nombre indiqué par l’article pour le périmètre expérimental ; ce n’est ni une statistique nationale ni un résultat de terrain.","pt":"Número informado no escopo experimental do artigo; não é estatística nacional nem resultado de campo.","tr":"Sayı, kaynak çalışmada bildirilen deney kapsamıdır; ulusal istatistik veya saha sonucu değildir."},"rowTranslations":[{"indicator":{"ar":"عدد المهام المقيمة من معيار Mind2Web","de":"Bewertete Aufgaben des Mind2Web-Benchmarks","en":"Tasks evaluated from the Mind2Web benchmark","es":"Tareas evaluadas del benchmark Mind2Web","fr":"Nombre de tâches évaluées du benchmark Mind2Web","pt":"Tarefas avaliadas do benchmark Mind2Web","tr":"Mind2Web kıyaslamasında incelenen görev sayısı"}}],"rows":[{"count":300,"indicator":"Tasks evaluated from the Mind2Web benchmark","released":"2026-10-09"}],"sourceUrls":["https://arxiv.org/html/2610.13703v1"],"title":{"ar":"نطاق الدراسة","de":"Umfang der Studie","en":"Study scope","es":"Alcance del estudio","fr":"Périmètre de l’étude","pt":"Escopo do estudo","tr":"Çalışmanın kapsamı"},"type":"table","updatedAt":"2026-10-12T23:24:06Z"}],"version":1},"data_downloads":[{"formats":{"csv":"https://newsverum.com/api/v1/articles/brazilian-researchers-benchmark-agentic-web-technology-stacks/data/study-experimental-scope?lang=fr&format=csv","json":"https://newsverum.com/api/v1/articles/brazilian-researchers-benchmark-agentic-web-technology-stacks/data/study-experimental-scope?lang=fr&format=json"},"id":"study-experimental-scope"}],"data_types":["table"],"editorial_illustration":{"alt":"Illustration conceptuelle de la technologie, des processeurs et des informations connectées.","asset_id":"newsverum-v1-technology","avif_variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.avif","width":480},{"height":480,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-720.avif","width":720},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.avif","width":960},{"height":800,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1200.avif","width":1200},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.avif","width":1536}],"credit":"Newsverum","documentary":false,"height":1024,"kind":"symbolic-editorial-illustration","language":"fr","scope":"topic","url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.webp","width":480},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.webp","width":960},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","width":1536}],"width":1536},"event_id":"event-1027a484-ace9-570e-94d4-47f9c7e21464","event_period":"2026-10-09","event_period_basis":"event-or-reference-period","id":"brazilian-researchers-benchmark-agentic-web-technology-stacks","image":null,"importance":0.6,"language":"fr","modified_at":"2026-10-12T23:33:38+00:00","publication_basis":"publication-record","published_at":"2026-10-12T23:33:38+00:00","reading_minutes":1,"region":"world","section_illustration":{"alt":"Illustration conceptuelle de la technologie, des processeurs et des informations connectées.","asset_id":"newsverum-v1-technology","avif_variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.avif","width":480},{"height":480,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-720.avif","width":720},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.avif","width":960},{"height":800,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1200.avif","width":1200},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.avif","width":1536}],"credit":"Newsverum","documentary":false,"height":1024,"kind":"symbolic-editorial-illustration","language":"fr","scope":"section","url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.webp","width":480},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.webp","width":960},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","width":1536}],"width":1536},"slug":"brazilian-researchers-benchmark-agentic-web-technology-stacks","sources":[{"checkedAt":"2026-10-13","name":"arXiv preprint by NIC.br and PUC-SP researchers","publishedAt":"2026-10-09","url":"https://arxiv.org/html/2610.13703v1"}],"summary":"Une étude de NIC.br et de PUC-SP a testé trois modèles, trois protocoles et quatre cadres sur 300 tâches Mind2Web.","text":"Une étude de NIC.br et de PUC-SP a testé trois modèles, trois protocoles et quatre cadres sur 300 tâches Mind2Web.\n\nDes chercheurs de NIC.br et de PUC-SP ont publié le 9 octobre une étude présentant MASTIF, un cadre destiné à comparer des combinaisons de technologies pour les systèmes multi-agents. L’évaluation a croisé trois modèles de langage, trois protocoles de communication et quatre cadres d’implémentation sur 300 tâches du benchmark Mind2Web.\n\nL’article rapporte des écarts selon les mesures — taux d’achèvement, durée, concision, usage des outils et stabilité des valeurs sociales — sans qu’une seule combinaison soit la meilleure partout. Les auteurs soulignent les limites des tâches et des modèles étudiés. Ces résultats constituent un point de référence expérimental et ne garantissent pas les performances d’agents en situation réelle.","title":"Des chercheurs brésiliens évaluent des piles technologiques pour agents d’IA","topics":[],"translations":[{"api_url":"https://newsverum.com/api/v1/articles/brazilian-researchers-benchmark-agentic-web-technology-stacks?lang=tr","language":"tr","url":"https://newsverum.com/tr/news/brazilian-researchers-benchmark-agentic-web-technology-stacks"},{"api_url":"https://newsverum.com/api/v1/articles/brazilian-researchers-benchmark-agentic-web-technology-stacks?lang=en","language":"en","url":"https://newsverum.com/en/news/brazilian-researchers-benchmark-agentic-web-technology-stacks"},{"api_url":"https://newsverum.com/api/v1/articles/brazilian-researchers-benchmark-agentic-web-technology-stacks?lang=ar","language":"ar","url":"https://newsverum.com/ar/news/brazilian-researchers-benchmark-agentic-web-technology-stacks"},{"api_url":"https://newsverum.com/api/v1/articles/brazilian-researchers-benchmark-agentic-web-technology-stacks?lang=fr","language":"fr","url":"https://newsverum.com/fr/news/brazilian-researchers-benchmark-agentic-web-technology-stacks"},{"api_url":"https://newsverum.com/api/v1/articles/brazilian-researchers-benchmark-agentic-web-technology-stacks?lang=es","language":"es","url":"https://newsverum.com/es/news/brazilian-researchers-benchmark-agentic-web-technology-stacks"},{"api_url":"https://newsverum.com/api/v1/articles/brazilian-researchers-benchmark-agentic-web-technology-stacks?lang=de","language":"de","url":"https://newsverum.com/de/news/brazilian-researchers-benchmark-agentic-web-technology-stacks"},{"api_url":"https://newsverum.com/api/v1/articles/brazilian-researchers-benchmark-agentic-web-technology-stacks?lang=pt","language":"pt","url":"https://newsverum.com/pt/news/brazilian-researchers-benchmark-agentic-web-technology-stacks"}],"url":"https://newsverum.com/fr/news/brazilian-researchers-benchmark-agentic-web-technology-stacks"},"version":"1"}