{"article":{"annotation":{"article_id":"researchers-coordinate-multi-session-olympiad-agents","available_at":"2026-10-13T00:52:23.455780Z","geography_revision":"ef6ee0010dda5fe7b240fd514749b43e214c57da73222d2e40ec83b276dd0977","id":"8eb266c0419c7dc02f8554f8eb89fd424b58e02ae39b03f4f3d71f6330a3b7b4","input_sha256":"f6675845b7b807ea5262f464f679a83aadb6f787441d12c421a5d0dbca077158","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/2610.13632v1"]}],"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/2610.13632v1"]}],"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/researchers-coordinate-multi-session-olympiad-agents?lang=de","category":"technology","content":{"key_points":[],"paragraphs":["Forschende stellten HOA vor, einen offenen Workflow, der mehrere Agentensitzungen bei schwierigen Mathematik- und Wissenschaftsaufgaben koordiniert. Er lässt Lösungskandidaten unabhängig prüfen, ergänzt fehlendes Fachwissen durch ein strukturiertes Wiki und kontrolliert Lean-formalisierte Beweise mit einem vertrauenswürdigen Verifikator.","Die Autoren berichten, dass HOA 672 PutnamBench-Aufgaben und 251 Aufgaben bei Lean-Eval löste. Die Experimente umfassen außerdem die offiziellen Aufgaben der Mathematik-, Physik-, Chemie- und Informatikolympiaden 2026; die Bewertung nutzt je nach Fach menschliche Prüfung, Codetests oder ein LLM-Urteil. Die Ergebnisse gelten für diese Aufgaben und Bewertungsverfahren und belegen keine allgemeine Fähigkeit zu wissenschaftlichen Entdeckungen."],"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":"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":"نتيجة PutnamBench في تقييم الورقة","de":"PutnamBench-Ergebnis in der Auswertung der Arbeit","en":"PutnamBench result in the paper's evaluation","es":"Resultado de PutnamBench en la evaluación del artículo","fr":"Résultat de PutnamBench dans l’évaluation de l’article","pt":"Resultado do PutnamBench na avaliação do artigo","tr":"Paper'ın deney raporundaki PutnamBench sonuçları"},"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":"مسائل PutnamBench التي حلها HOA","de":"Mit HOA gelöste PutnamBench-Aufgaben","en":"PutnamBench problems solved with HOA","es":"Problemas de PutnamBench resueltos con HOA","fr":"Problèmes PutnamBench résolus avec HOA","pt":"Problemas do PutnamBench resolvidos com HOA","tr":"HOA ile çözülen PutnamBench problemi"},"scope":{"ar":"نتيجة PutnamBench في تقييم الورقة","de":"PutnamBench-Ergebnis in der Auswertung der Arbeit","en":"PutnamBench result in the paper's evaluation","es":"Resultado de PutnamBench en la evaluación del artículo","fr":"Résultat de PutnamBench dans l’évaluation de l’article","pt":"Resultado do PutnamBench na avaliação do artigo","tr":"Paper'ın deney raporundaki PutnamBench sonuçları"}}],"rows":[{"metric":"PutnamBench problems solved with HOA","scope":"PutnamBench result in the paper's evaluation","value":672}],"sourceUrls":["https://arxiv.org/html/2610.13632v1"],"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":"نتيجة Lean-Eval في تقييم الورقة","de":"Lean-Eval-Ergebnis in der Auswertung der Arbeit","en":"Lean-Eval result in the paper's evaluation","es":"Resultado de Lean-Eval en la evaluación del artículo","fr":"Résultat de Lean-Eval dans l’évaluation de l’article","pt":"Resultado do Lean-Eval na avaliação do artigo","tr":"Paper'ın deney raporundaki Lean-Eval sonuçları"},"id":"reported-result-2","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":"مسائل Lean-Eval التي حلها HOA","de":"Mit HOA gelöste Lean-Eval-Aufgaben","en":"Lean-Eval problems solved with HOA","es":"Problemas de Lean-Eval resueltos con HOA","fr":"Problèmes Lean-Eval résolus avec HOA","pt":"Problemas do Lean-Eval resolvidos com HOA","tr":"HOA ile çözülen Lean-Eval problemi"},"scope":{"ar":"نتيجة Lean-Eval في تقييم الورقة","de":"Lean-Eval-Ergebnis in der Auswertung der Arbeit","en":"Lean-Eval result in the paper's evaluation","es":"Resultado de Lean-Eval en la evaluación del artículo","fr":"Résultat de Lean-Eval dans l’évaluation de l’article","pt":"Resultado do Lean-Eval na avaliação do artigo","tr":"Paper'ın deney raporundaki Lean-Eval sonuçları"}}],"rows":[{"metric":"Lean-Eval problems solved with HOA","scope":"Lean-Eval result in the paper's evaluation","value":251}],"sourceUrls":["https://arxiv.org/html/2610.13632v1"],"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/researchers-coordinate-multi-session-olympiad-agents/data/reported-result-1?lang=de&format=csv","json":"https://newsverum.com/api/v1/articles/researchers-coordinate-multi-session-olympiad-agents/data/reported-result-1?lang=de&format=json"},"id":"reported-result-1"},{"formats":{"csv":"https://newsverum.com/api/v1/articles/researchers-coordinate-multi-session-olympiad-agents/data/reported-result-2?lang=de&format=csv","json":"https://newsverum.com/api/v1/articles/researchers-coordinate-multi-session-olympiad-agents/data/reported-result-2?lang=de&format=json"},"id":"reported-result-2"}],"data_types":["table"],"editorial_illustration":{"alt":"Konzeptionelle Darstellung von Technologie, Prozessoren und verbundenen Informationen.","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":"de","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-9e4ff9c7-3d7e-5289-9450-84e0c856f394","event_period":"2026-10-09","event_period_basis":"event-or-reference-period","id":"researchers-coordinate-multi-session-olympiad-agents","image":null,"importance":0.6,"language":"de","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":"Konzeptionelle Darstellung von Technologie, Prozessoren und verbundenen Informationen.","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":"de","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":"researchers-coordinate-multi-session-olympiad-agents","sources":[{"checkedAt":"2026-10-13","name":"arXiv preprint by Tsinghua University, NVIDIA and collaborating researchers","publishedAt":"2026-10-09","url":"https://arxiv.org/html/2610.13632v1"}],"summary":"HOA verbindet unabhängige Prüfung, strukturierte Wissensnotizen und formale Verifikation.","text":"HOA verbindet unabhängige Prüfung, strukturierte Wissensnotizen und formale Verifikation.\n\nForschende stellten HOA vor, einen offenen Workflow, der mehrere Agentensitzungen bei schwierigen Mathematik- und Wissenschaftsaufgaben koordiniert. Er lässt Lösungskandidaten unabhängig prüfen, ergänzt fehlendes Fachwissen durch ein strukturiertes Wiki und kontrolliert Lean-formalisierte Beweise mit einem vertrauenswürdigen Verifikator.\n\nDie Autoren berichten, dass HOA 672 PutnamBench-Aufgaben und 251 Aufgaben bei Lean-Eval löste. Die Experimente umfassen außerdem die offiziellen Aufgaben der Mathematik-, Physik-, Chemie- und Informatikolympiaden 2026; die Bewertung nutzt je nach Fach menschliche Prüfung, Codetests oder ein LLM-Urteil. Die Ergebnisse gelten für diese Aufgaben und Bewertungsverfahren und belegen keine allgemeine Fähigkeit zu wissenschaftlichen Entdeckungen.","title":"Forschende stellen einen Mehrsitzungs-Workflow für Olympiade-Agenten vor","topics":[],"translations":[{"api_url":"https://newsverum.com/api/v1/articles/researchers-coordinate-multi-session-olympiad-agents?lang=tr","language":"tr","url":"https://newsverum.com/tr/news/researchers-coordinate-multi-session-olympiad-agents"},{"api_url":"https://newsverum.com/api/v1/articles/researchers-coordinate-multi-session-olympiad-agents?lang=en","language":"en","url":"https://newsverum.com/en/news/researchers-coordinate-multi-session-olympiad-agents"},{"api_url":"https://newsverum.com/api/v1/articles/researchers-coordinate-multi-session-olympiad-agents?lang=ar","language":"ar","url":"https://newsverum.com/ar/news/researchers-coordinate-multi-session-olympiad-agents"},{"api_url":"https://newsverum.com/api/v1/articles/researchers-coordinate-multi-session-olympiad-agents?lang=fr","language":"fr","url":"https://newsverum.com/fr/news/researchers-coordinate-multi-session-olympiad-agents"},{"api_url":"https://newsverum.com/api/v1/articles/researchers-coordinate-multi-session-olympiad-agents?lang=es","language":"es","url":"https://newsverum.com/es/news/researchers-coordinate-multi-session-olympiad-agents"},{"api_url":"https://newsverum.com/api/v1/articles/researchers-coordinate-multi-session-olympiad-agents?lang=de","language":"de","url":"https://newsverum.com/de/news/researchers-coordinate-multi-session-olympiad-agents"},{"api_url":"https://newsverum.com/api/v1/articles/researchers-coordinate-multi-session-olympiad-agents?lang=pt","language":"pt","url":"https://newsverum.com/pt/news/researchers-coordinate-multi-session-olympiad-agents"}],"url":"https://newsverum.com/de/news/researchers-coordinate-multi-session-olympiad-agents"},"version":"1"}