{"article":{"annotation":{"article_id":"longharness-tests-evidence-management-for-long-context-agents","available_at":"2026-10-13T00:52:07.251918Z","geography_revision":"ef6ee0010dda5fe7b240fd514749b43e214c57da73222d2e40ec83b276dd0977","id":"9bf61481db4d4e67b2aa3c9fcfcd62ce3aaa06dceb0cccdf17ce693fcd8b2526","input_sha256":"87e3921b6fcd6213a9e6987e6cb05442d41991cdd0467c791d54299e3d47ef3c","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/2610.13075v1"]}],"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/2610.13075v1"]}],"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/longharness-tests-evidence-management-for-long-context-agents?lang=en","category":"technology","content":{"key_points":[],"paragraphs":["Researchers affiliated with Fudan University, Shanghai AI Laboratory and Peking University in China introduced LongHarness. The system manages source-linked evidence across long document collections; as new evidence arrives, it updates both the evidence pool and provisional conclusions.","In the evaluation on the first version of OfficeQA Pro, the paper reports a 60.2% exact-match rate with GLM-5.3-Flash. The authors describe a substantial increase over direct model use, but the result is limited to the constructed benchmark and the tested model and retrieval setup. It does not establish the same performance in every real long-context workflow."],"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":"النسبة المئوية","de":"Prozent","en":"Percent","es":"Porcentaje","fr":"Pourcentage","pt":"Percentual","tr":"Yüzde"},"type":"number","unit":"percent"},{"key":"scope","label":{"ar":"النطاق","de":"Umfang","en":"Scope","es":"Alcance","fr":"Périmètre","pt":"Escopo","tr":"Kapsam"},"language":"en","type":"text"}],"description":{"ar":"OfficeQA Pro V1؛ معيار يضم نحو 100 مليون رمز؛ تطابق تام","de":"OfficeQA Pro V1; Benchmark mit etwa 100 Millionen Token; Exact Match","en":"OfficeQA Pro V1; benchmark of about 100 million tokens; exact match","es":"OfficeQA Pro V1; benchmark de unos 100 millones de tokens; coincidencia exacta","fr":"OfficeQA Pro V1; benchmark d’environ 100 millions de tokens; exact match","pt":"OfficeQA Pro V1; benchmark com cerca de 100 milhões de tokens; correspondência exata","tr":"OfficeQA Pro V1; yaklaşık 100 milyon tokenlık benchmark; exact match"},"id":"reported-result-1","methodology":{"ar":"تقتصر القيمة على تجربة المعيار المذكورة في الورقة؛ وليست نتيجة ميدانية أو ضماناً عاماً للأداء.","de":"Der Wert ist auf das im Artikel beschriebene Benchmark-Experiment beschränkt; er ist kein Feldergebnis und keine allgemeine Leistungsgarantie.","en":"The value is limited to the benchmark experiment reported in the paper; it is not a field result or general performance guarantee.","es":"El valor se limita al experimento de benchmark descrito en el artículo; no es un resultado de campo ni una garantía general.","fr":"La valeur se limite à l’expérience de benchmark décrite dans l’article; ce n’est ni un résultat de terrain ni une garantie générale.","pt":"O valor se limita ao experimento de benchmark descrito no artigo; não é um resultado de campo nem uma garantia geral.","tr":"Değer, makalenin belirttiği benchmark deneyiyle sınırlıdır; saha sonucu veya genel performans garantisi değildir."},"rowTranslations":[{"metric":{"ar":"معدل التطابق التام لـ GLM-5.3-Flash على OfficeQA Pro V1","de":"Exact-Match-Rate von GLM-5.3-Flash auf OfficeQA Pro V1","en":"GLM-5.3-Flash exact-match rate on OfficeQA Pro V1","es":"Tasa de coincidencia exacta de GLM-5.3-Flash en OfficeQA Pro V1","fr":"Taux d’exact match de GLM-5.3-Flash sur OfficeQA Pro V1","pt":"Taxa de correspondência exata do GLM-5.3-Flash no OfficeQA Pro V1","tr":"OfficeQA Pro ilk sürümünde GLM-5.3-Flash tam eşleşme oranı"},"scope":{"ar":"OfficeQA Pro V1؛ معيار يضم نحو 100 مليون رمز؛ تطابق تام","de":"OfficeQA Pro V1; Benchmark mit etwa 100 Millionen Token; Exact Match","en":"OfficeQA Pro V1; benchmark of about 100 million tokens; exact match","es":"OfficeQA Pro V1; benchmark de unos 100 millones de tokens; coincidencia exacta","fr":"OfficeQA Pro V1; benchmark d’environ 100 millions de tokens; exact match","pt":"OfficeQA Pro V1; benchmark com cerca de 100 milhões de tokens; correspondência exata","tr":"OfficeQA Pro V1; yaklaşık 100 milyon tokenlık benchmark; exact match"}}],"rows":[{"metric":"GLM-5.3-Flash exact-match rate on OfficeQA Pro V1","scope":"OfficeQA Pro V1; benchmark of about 100 million tokens; exact match","value":60.2}],"sourceUrls":["https://arxiv.org/html/2610.13075v1"],"title":{"ar":"نتيجة البحث","de":"Forschungsergebnis","en":"Research result","es":"Resultado del estudio","fr":"Résultat de l’étude","pt":"Resultado da pesquisa","tr":"Araştırma sonucu"},"type":"table","updatedAt":"2026-10-13T00:17:05Z"}],"version":1},"data_downloads":[{"formats":{"csv":"https://newsverum.com/api/v1/articles/longharness-tests-evidence-management-for-long-context-agents/data/reported-result-1?lang=en&format=csv","json":"https://newsverum.com/api/v1/articles/longharness-tests-evidence-management-for-long-context-agents/data/reported-result-1?lang=en&format=json"},"id":"reported-result-1"}],"data_types":["table"],"editorial_illustration":{"alt":"Conceptual illustration of technology, processors and connected information.","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":"en","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-44b33fab-2f6c-5df1-b327-172be892c694","event_period":"2026-10-09","event_period_basis":"event-or-reference-period","id":"longharness-tests-evidence-management-for-long-context-agents","image":null,"importance":0.6,"language":"en","modified_at":"2026-10-13T00:51:40+00:00","publication_basis":"publication-record","published_at":"2026-10-13T00:51:40+00:00","reading_minutes":1,"region":"world","section_illustration":{"alt":"Conceptual illustration of technology, processors and connected information.","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":"en","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":"longharness-tests-evidence-management-for-long-context-agents","sources":[{"checkedAt":"2026-10-13","name":"arXiv preprint by researchers affiliated with Fudan University, Shanghai AI Laboratory, Peking University and other Chinese institutions","publishedAt":"2026-10-09","url":"https://arxiv.org/html/2610.13075v1"}],"summary":"The framework supports agent answers by updating evidence and conclusions together across long documents.","text":"The framework supports agent answers by updating evidence and conclusions together across long documents.\n\nResearchers affiliated with Fudan University, Shanghai AI Laboratory and Peking University in China introduced LongHarness. The system manages source-linked evidence across long document collections; as new evidence arrives, it updates both the evidence pool and provisional conclusions.\n\nIn the evaluation on the first version of OfficeQA Pro, the paper reports a 60.2% exact-match rate with GLM-5.3-Flash. The authors describe a substantial increase over direct model use, but the result is limited to the constructed benchmark and the tested model and retrieval setup. It does not establish the same performance in every real long-context workflow.","title":"LongHarness tests evidence management for long-context agents","topics":[],"translations":[{"api_url":"https://newsverum.com/api/v1/articles/longharness-tests-evidence-management-for-long-context-agents?lang=tr","language":"tr","url":"https://newsverum.com/tr/news/longharness-tests-evidence-management-for-long-context-agents"},{"api_url":"https://newsverum.com/api/v1/articles/longharness-tests-evidence-management-for-long-context-agents?lang=en","language":"en","url":"https://newsverum.com/en/news/longharness-tests-evidence-management-for-long-context-agents"},{"api_url":"https://newsverum.com/api/v1/articles/longharness-tests-evidence-management-for-long-context-agents?lang=ar","language":"ar","url":"https://newsverum.com/ar/news/longharness-tests-evidence-management-for-long-context-agents"},{"api_url":"https://newsverum.com/api/v1/articles/longharness-tests-evidence-management-for-long-context-agents?lang=fr","language":"fr","url":"https://newsverum.com/fr/news/longharness-tests-evidence-management-for-long-context-agents"},{"api_url":"https://newsverum.com/api/v1/articles/longharness-tests-evidence-management-for-long-context-agents?lang=es","language":"es","url":"https://newsverum.com/es/news/longharness-tests-evidence-management-for-long-context-agents"},{"api_url":"https://newsverum.com/api/v1/articles/longharness-tests-evidence-management-for-long-context-agents?lang=de","language":"de","url":"https://newsverum.com/de/news/longharness-tests-evidence-management-for-long-context-agents"},{"api_url":"https://newsverum.com/api/v1/articles/longharness-tests-evidence-management-for-long-context-agents?lang=pt","language":"pt","url":"https://newsverum.com/pt/news/longharness-tests-evidence-management-for-long-context-agents"}],"url":"https://newsverum.com/en/news/longharness-tests-evidence-management-for-long-context-agents"},"version":"1"}