{"article":{"annotation":{"article_id":"multi-agent-session-alternation-tests-machine-learning-engineering","available_at":"2026-10-13T00:52:16.046437Z","geography_revision":"ef6ee0010dda5fe7b240fd514749b43e214c57da73222d2e40ec83b276dd0977","id":"cbbb7175821fee0a13e298e7658e769e66dc065fcb79ddbe76a37e62f8a3318e","input_sha256":"6512fc4c0224e8bbcd7e6c2fe728a9633e4e5132f1585ebabdad6bd6aba48848","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":"CN","evidence":[{"field":"country","language":"en","note":"Explicit preserved editorial country/region; no city or national centroid inferred","source_urls":["https://arxiv.org/html/2610.13494v1"]}],"geometry":null,"id":"iso3166-1:CN","kind":"country-or-area","labels":{"ar":"الصين","en":"China","es":"China","fr":"Chine"},"match_status":"candidate","precision":"regional","role":"coverage","uncertainty_m":null}],"rules_sha256":"fb5ad3c27c91cb840f7a0a05f7f64a5cb26ad0374409ff9457f277c7092e22b4","schema_version":1,"subjects":[{"concept_id":"medtop:13000000","confidence":null,"confidence_method":null,"evidence":[{"field":"category+topics","language":"en","note":"Preserved editorial category/topic; broad candidate only","source_urls":["https://arxiv.org/html/2610.13494v1"]}],"method":"controlled-rules-v1","rule_id":"technology-broad","status":"candidate"}],"taxonomy_revision":"1f2db31d811fca07e99b16d402c10e2cc2965c9df1c7b41d9be348b40a24e7fb","taxonomy_version":"IPTC Media Topics 2026-Q2"},"api_url":"https://newsverum.com/api/v1/articles/multi-agent-session-alternation-tests-machine-learning-engineering?lang=tr","category":"technology","content":{"key_points":[],"paragraphs":["Tsinghua, Zhejiang ve NVIDIA bağlantılı araştırmacılar, uzun makine öğrenmesi mühendisliği görevlerinde iki ajanın oturumlarını dönüşümlü çalıştıran Humanize MLE Agents yöntemini sundu. Her oturum en fazla belirli sayıda deneye kadar sürüyor; oturum bağlamı sıfırlansa da kod, modeller ve önceki sonuçlar ortak çalışma alanında kalıyor.","MLE-bench’teki 75 Kaggle görevi üzerinde yazarlar, iş akışının yüzde 78,2 herhangi madalya oranına ulaştığını ve en güçlü açık kaynak karşılaştırmayı daha düşük zaman bütçesiyle geçtiğini bildirdi. Bu, belirli bir yarışma kümesi ve ajan eşleşmeleri için raporlanan bir sonuçtur; farklı model sürümlerinde veya gerçek mühendislik projelerinde aynı kazanımı garanti etmez."],"sections":[]},"corrections":[],"country":"CN","data":{"blocks":[{"columns":[{"key":"metric","label":{"ar":"المقياس","de":"Messgröße","en":"Measure","es":"Medida","fr":"Mesure","pt":"Medida","tr":"Ölçüt"},"language":"en","type":"text"},{"key":"value","label":{"ar":"القيمة المعلنة","de":"Berichteter Wert","en":"Reported value","es":"Valor comunicado","fr":"Valeur rapportée","pt":"Valor informado","tr":"Bildirilen değer"},"type":"number","unit":"percent"},{"key":"scope","label":{"ar":"نطاق التجربة","de":"Versuchsumfang","en":"Experimental scope","es":"Alcance experimental","fr":"Périmètre expérimental","pt":"Escopo experimental","tr":"Deney kapsamı"},"language":"en","type":"text"}],"description":{"ar":"75 مهمة Kaggle؛ تقييم MLE-bench","de":"75 Kaggle-Aufgaben; MLE-bench-Auswertung","en":"75 Kaggle tasks; MLE-bench evaluation","es":"75 tareas de Kaggle; evaluación MLE-bench","fr":"75 tâches Kaggle; évaluation MLE-bench","pt":"75 tarefas do Kaggle; avaliação MLE-bench","tr":"75 Kaggle görevi; MLE-bench değerlendirmesi"},"id":"reported-result-1","methodology":{"ar":"القيم من تجارب المعيار التي حددتها الورقة؛ وليست قياسات ميدانية أو ضمانات أداء عامة.","de":"Die Werte stammen aus den im Artikel beschriebenen Benchmark-Experimenten; sie sind weder Feldmessungen noch allgemeine Leistungsgarantien.","en":"Values come from the paper's stated benchmark experiments; they are not field measurements or general performance guarantees.","es":"Las cifras proceden de los experimentos de benchmark descritos en el artículo; no son mediciones de campo ni una garantía general de rendimiento.","fr":"Les valeurs proviennent des expériences de benchmark décrites dans l’article; elles ne constituent ni des mesures de terrain ni une garantie générale de performance.","pt":"Os valores vêm dos experimentos de benchmark descritos no artigo; não são medições de campo nem garantias gerais de desempenho.","tr":"Rakamlar makalenin tanımladığı kıyaslama deneylerine aittir; saha ölçümü veya genel performans garantisi değildir."},"rowTranslations":[{"metric":{"ar":"معدل الفوز بأي ميدالية في مهام Kaggle ضمن MLE-bench","de":"Any-Medal-Rate bei Kaggle-Aufgaben in MLE-bench","en":"Any-medal rate on MLE-bench Kaggle tasks","es":"Tasa de obtención de alguna medalla en tareas Kaggle de MLE-bench","fr":"Taux de médaille obtenue sur les tâches Kaggle de MLE-bench","pt":"Taxa de obtenção de alguma medalha em tarefas Kaggle do MLE-bench","tr":"MLE-bench Kaggle görevlerinde herhangi madalya oranı"},"scope":{"ar":"75 مهمة Kaggle؛ تقييم MLE-bench","de":"75 Kaggle-Aufgaben; MLE-bench-Auswertung","en":"75 Kaggle tasks; MLE-bench evaluation","es":"75 tareas de Kaggle; evaluación MLE-bench","fr":"75 tâches Kaggle; évaluation MLE-bench","pt":"75 tarefas do Kaggle; avaliação MLE-bench","tr":"75 Kaggle görevi; MLE-bench değerlendirmesi"}}],"rows":[{"metric":"Any-medal rate on MLE-bench Kaggle tasks","scope":"75 Kaggle tasks; MLE-bench evaluation","value":78.2}],"sourceUrls":["https://arxiv.org/html/2610.13494v1"],"title":{"ar":"المقياس","de":"Messgröße","en":"Measure","es":"Medida","fr":"Mesure","pt":"Medida","tr":"Ölçüt"},"type":"table","updatedAt":"2026-10-13T00:12:48Z"},{"columns":[{"key":"metric","label":{"ar":"المقياس","de":"Messgröße","en":"Measure","es":"Medida","fr":"Mesure","pt":"Medida","tr":"Ölçüt"},"language":"en","type":"text"},{"key":"value","label":{"ar":"القيمة المعلنة","de":"Berichteter Wert","en":"Reported value","es":"Valor comunicado","fr":"Valeur rapportée","pt":"Valor informado","tr":"Bildirilen değer"},"type":"number","unit":"count"},{"key":"scope","label":{"ar":"نطاق التجربة","de":"Versuchsumfang","en":"Experimental scope","es":"Alcance experimental","fr":"Périmètre expérimental","pt":"Escopo experimental","tr":"Deney kapsamı"},"language":"en","type":"text"}],"description":{"ar":"مجموعة مهام Kaggle المذكورة في تقييم MLE-bench","de":"Im MLE-bench-Test ausgewerteter Kaggle-Aufgabensatz","en":"Kaggle task set reported in the MLE-bench evaluation","es":"Conjunto de tareas Kaggle informado en la evaluación MLE-bench","fr":"Ensemble de tâches Kaggle indiqué dans l’évaluation MLE-bench","pt":"Conjunto de tarefas Kaggle informado na avaliação do MLE-bench","tr":"MLE-bench değerlendirmesinde raporlanan Kaggle görev kümesi"},"id":"result-75","methodology":{"ar":"القيم من تجارب المعيار التي حددتها الورقة؛ وليست قياسات ميدانية أو ضمانات أداء عامة.","de":"Die Werte stammen aus den im Artikel beschriebenen Benchmark-Experimenten; sie sind weder Feldmessungen noch allgemeine Leistungsgarantien.","en":"Values come from the paper's stated benchmark experiments; they are not field measurements or general performance guarantees.","es":"Las cifras proceden de los experimentos de benchmark descritos en el artículo; no son mediciones de campo ni una garantía general de rendimiento.","fr":"Les valeurs proviennent des expériences de benchmark décrites dans l’article; elles ne constituent ni des mesures de terrain ni une garantie générale de performance.","pt":"Os valores vêm dos experimentos de benchmark descritos no artigo; não são medições de campo nem garantias gerais de desempenho.","tr":"Rakamlar makalenin tanımladığı kıyaslama deneylerine aittir; saha ölçümü veya genel performans garantisi değildir."},"rowTranslations":[{"metric":{"ar":"عدد مهام Kaggle في MLE-bench","de":"Zahl der Kaggle-Aufgaben in MLE-bench","en":"Number of MLE-bench Kaggle tasks","es":"Número de tareas Kaggle de MLE-bench","fr":"Nombre de tâches Kaggle de MLE-bench","pt":"Número de tarefas Kaggle do MLE-bench","tr":"MLE-bench Kaggle görev sayısı"},"scope":{"ar":"مجموعة مهام Kaggle المذكورة في تقييم MLE-bench","de":"Im MLE-bench-Test ausgewerteter Kaggle-Aufgabensatz","en":"Kaggle task set reported in the MLE-bench evaluation","es":"Conjunto de tareas Kaggle informado en la evaluación MLE-bench","fr":"Ensemble de tâches Kaggle indiqué dans l’évaluation MLE-bench","pt":"Conjunto de tarefas Kaggle informado na avaliação do MLE-bench","tr":"MLE-bench değerlendirmesinde raporlanan Kaggle görev kümesi"}}],"rows":[{"metric":"Number of MLE-bench Kaggle tasks","scope":"Kaggle task set reported in the MLE-bench evaluation","value":75}],"sourceUrls":["https://arxiv.org/html/2610.13494v1"],"title":{"ar":"المقياس","de":"Messgröße","en":"Measure","es":"Medida","fr":"Mesure","pt":"Medida","tr":"Ölçüt"},"type":"table","updatedAt":"2026-10-13T00:12:48Z"}],"version":1},"data_downloads":[{"formats":{"csv":"https://newsverum.com/api/v1/articles/multi-agent-session-alternation-tests-machine-learning-engineering/data/reported-result-1?lang=tr&format=csv","json":"https://newsverum.com/api/v1/articles/multi-agent-session-alternation-tests-machine-learning-engineering/data/reported-result-1?lang=tr&format=json"},"id":"reported-result-1"},{"formats":{"csv":"https://newsverum.com/api/v1/articles/multi-agent-session-alternation-tests-machine-learning-engineering/data/result-75?lang=tr&format=csv","json":"https://newsverum.com/api/v1/articles/multi-agent-session-alternation-tests-machine-learning-engineering/data/result-75?lang=tr&format=json"},"id":"result-75"}],"data_types":["table"],"editorial_illustration":{"alt":"Teknoloji, işlemci ve bağlantılı bilginin kavramsal illüstrasyonu.","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":"tr","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-5feb6b74-59c2-5e3f-984a-af92c529aa84","event_period":"2026-10-09","event_period_basis":"event-or-reference-period","id":"multi-agent-session-alternation-tests-machine-learning-engineering","image":null,"importance":0.6,"language":"tr","modified_at":"2026-10-13T00:51:41+00:00","publication_basis":"publication-record","published_at":"2026-10-13T00:51:41+00:00","reading_minutes":1,"region":"world","section_illustration":{"alt":"Teknoloji, işlemci ve bağlantılı bilginin kavramsal illüstrasyonu.","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":"tr","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":"multi-agent-session-alternation-tests-machine-learning-engineering","sources":[{"checkedAt":"2026-10-13","name":"arXiv preprint by Tsinghua University, Zhejiang University and collaborating researchers","publishedAt":"2026-10-09","url":"https://arxiv.org/html/2610.13494v1"}],"summary":"Humanize MLE Agents, ortak çalışma alanını korurken oturum bağlamını sıfırlayan iki ajanı sırayla çalıştırıyor.","text":"Humanize MLE Agents, ortak çalışma alanını korurken oturum bağlamını sıfırlayan iki ajanı sırayla çalıştırıyor.\n\nTsinghua, Zhejiang ve NVIDIA bağlantılı araştırmacılar, uzun makine öğrenmesi mühendisliği görevlerinde iki ajanın oturumlarını dönüşümlü çalıştıran Humanize MLE Agents yöntemini sundu. Her oturum en fazla belirli sayıda deneye kadar sürüyor; oturum bağlamı sıfırlansa da kod, modeller ve önceki sonuçlar ortak çalışma alanında kalıyor.\n\nMLE-bench’teki 75 Kaggle görevi üzerinde yazarlar, iş akışının yüzde 78,2 herhangi madalya oranına ulaştığını ve en güçlü açık kaynak karşılaştırmayı daha düşük zaman bütçesiyle geçtiğini bildirdi. Bu, belirli bir yarışma kümesi ve ajan eşleşmeleri için raporlanan bir sonuçtur; farklı model sürümlerinde veya gerçek mühendislik projelerinde aynı kazanımı garanti etmez.","title":"Araştırmacılar makine öğrenmesi görevlerinde ajan oturumlarını dönüşümlü kullandı","topics":[],"translations":[{"api_url":"https://newsverum.com/api/v1/articles/multi-agent-session-alternation-tests-machine-learning-engineering?lang=tr","language":"tr","url":"https://newsverum.com/tr/news/multi-agent-session-alternation-tests-machine-learning-engineering"},{"api_url":"https://newsverum.com/api/v1/articles/multi-agent-session-alternation-tests-machine-learning-engineering?lang=en","language":"en","url":"https://newsverum.com/en/news/multi-agent-session-alternation-tests-machine-learning-engineering"},{"api_url":"https://newsverum.com/api/v1/articles/multi-agent-session-alternation-tests-machine-learning-engineering?lang=ar","language":"ar","url":"https://newsverum.com/ar/news/multi-agent-session-alternation-tests-machine-learning-engineering"},{"api_url":"https://newsverum.com/api/v1/articles/multi-agent-session-alternation-tests-machine-learning-engineering?lang=fr","language":"fr","url":"https://newsverum.com/fr/news/multi-agent-session-alternation-tests-machine-learning-engineering"},{"api_url":"https://newsverum.com/api/v1/articles/multi-agent-session-alternation-tests-machine-learning-engineering?lang=es","language":"es","url":"https://newsverum.com/es/news/multi-agent-session-alternation-tests-machine-learning-engineering"},{"api_url":"https://newsverum.com/api/v1/articles/multi-agent-session-alternation-tests-machine-learning-engineering?lang=de","language":"de","url":"https://newsverum.com/de/news/multi-agent-session-alternation-tests-machine-learning-engineering"},{"api_url":"https://newsverum.com/api/v1/articles/multi-agent-session-alternation-tests-machine-learning-engineering?lang=pt","language":"pt","url":"https://newsverum.com/pt/news/multi-agent-session-alternation-tests-machine-learning-engineering"}],"url":"https://newsverum.com/tr/news/multi-agent-session-alternation-tests-machine-learning-engineering"},"version":"1"}