{"article":{"annotation":{"article_id":"competence-aware-orchestration-adjusts-llm-agent-teams","available_at":"2026-10-13T00:51:59.312846Z","geography_revision":"ef6ee0010dda5fe7b240fd514749b43e214c57da73222d2e40ec83b276dd0977","id":"f2a7b7e771e220e883c10316ed5b179d21d9c4c0dd0133cb6874c9092e996c00","input_sha256":"6ee401f3607d4858a023cc0b556ef4fca0569e42a50f0f8796449a7121f8994e","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":"HK","evidence":[{"field":"country","language":"en","note":"Explicit preserved editorial country/region; no city or national centroid inferred","source_urls":["https://arxiv.org/html/2610.13144v1"]}],"geometry":null,"id":"iso3166-1:HK","kind":"country-or-area","labels":{"ar":"الصين، منطقة هونغ كونغ الإدارية الخاصة","en":"China, Hong Kong Special Administrative Region","es":"China, región administrativa especial de Hong Kong","fr":"Chine, région administrative spéciale de Hong Kong"},"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/2610.13144v1"]}],"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/competence-aware-orchestration-adjusts-llm-agent-teams?lang=de","category":"technology","content":{"key_points":[],"paragraphs":["Forschende der Hong Kong Polytechnic University stellten ein Framework zur kompetenzbewussten Koordination von Agenten vor. Es vergleicht den Aufgabenkontext mit dem Fähigkeitsprofil jedes Modells und passt Rollenverteilung sowie Kommunikationsgraph an, statt für jede Aufgabe dieselbe Multi-Agenten-Anordnung zu verwenden.","Bei den Benchmarks berichten die Autoren in ausgewählten Konfigurationen leistungsstarker Modelle von 36,26 % weniger Tokenverbrauch bei gleichbleibenden Durchschnittswerten. Das Ergebnis bezieht sich auf GPT-4o-basierte Auswertungen und festgelegte Benchmark-Aufgaben; die Arbeit zeigt nicht, dass Fähigkeitsprofile bei anderen Modellen oder realen Workflows ebenso genau abgeleitet werden können."],"sections":[]},"corrections":[],"country":"HK","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":"ستة معايير؛ تجارب قائمة على GPT-4o؛ متوسط استخدام الرموز في إعدادات مختارة","de":"Sechs Benchmarks; GPT-4o-basierte Versuche; mittlerer Tokenverbrauch in ausgewählten Konfigurationen","en":"Six benchmarks; GPT-4o-based experiments; average token use in selected configurations","es":"Seis benchmarks; experimentos basados en GPT-4o; uso medio de tokens en ciertas configuraciones","fr":"Six benchmarks; expériences basées sur GPT-4o; usage moyen des tokens dans certaines configurations","pt":"Seis benchmarks; experimentos baseados em GPT-4o; uso médio de tokens em configurações selecionadas","tr":"GPT-4o tabanlı benchmark deneyi; seçili düzenlerde ortalama token kullanımı"},"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":"انخفاض استخدام الرموز في إعدادات مختارة لنماذج قوية","de":"Token-Einsparung in ausgewählten Konfigurationen leistungsstarker Modelle","en":"Token-use reduction in selected strong-model configurations","es":"Reducción del uso de tokens en ciertas configuraciones de modelos potentes","fr":"Réduction des tokens dans certaines configurations de modèles performants","pt":"Redução do uso de tokens em configurações selecionadas de modelos fortes","tr":"Seçilmiş güçlü model düzenlerinde token kullanımındaki azalma"},"scope":{"ar":"ستة معايير؛ تجارب قائمة على GPT-4o؛ متوسط استخدام الرموز في إعدادات مختارة","de":"Sechs Benchmarks; GPT-4o-basierte Versuche; mittlerer Tokenverbrauch in ausgewählten Konfigurationen","en":"Six benchmarks; GPT-4o-based experiments; average token use in selected configurations","es":"Seis benchmarks; experimentos basados en GPT-4o; uso medio de tokens en ciertas configuraciones","fr":"Six benchmarks; expériences basées sur GPT-4o; usage moyen des tokens dans certaines configurations","pt":"Seis benchmarks; experimentos baseados em GPT-4o; uso médio de tokens em configurações selecionadas","tr":"GPT-4o tabanlı benchmark deneyi; seçili düzenlerde ortalama token kullanımı"}}],"rows":[{"metric":"Token-use reduction in selected strong-model configurations","scope":"Six benchmarks; GPT-4o-based experiments; average token use in selected configurations","value":36.26}],"sourceUrls":["https://arxiv.org/html/2610.13144v1"],"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/competence-aware-orchestration-adjusts-llm-agent-teams/data/reported-result-1?lang=de&format=csv","json":"https://newsverum.com/api/v1/articles/competence-aware-orchestration-adjusts-llm-agent-teams/data/reported-result-1?lang=de&format=json"},"id":"reported-result-1"}],"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-10d387e3-7134-5a56-9a16-0b8714c95de0","event_period":"2026-10-09","event_period_basis":"event-or-reference-period","id":"competence-aware-orchestration-adjusts-llm-agent-teams","image":null,"importance":0.6,"language":"de","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":"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":"competence-aware-orchestration-adjusts-llm-agent-teams","sources":[{"checkedAt":"2026-10-13","name":"arXiv preprint by Hong Kong Polytechnic University researchers","publishedAt":"2026-10-09","url":"https://arxiv.org/html/2610.13144v1"}],"summary":"Das Framework passt Rollen und Kommunikation der Agenten an aufgabenspezifische Kompetenzen an.","text":"Das Framework passt Rollen und Kommunikation der Agenten an aufgabenspezifische Kompetenzen an.\n\nForschende der Hong Kong Polytechnic University stellten ein Framework zur kompetenzbewussten Koordination von Agenten vor. Es vergleicht den Aufgabenkontext mit dem Fähigkeitsprofil jedes Modells und passt Rollenverteilung sowie Kommunikationsgraph an, statt für jede Aufgabe dieselbe Multi-Agenten-Anordnung zu verwenden.\n\nBei den Benchmarks berichten die Autoren in ausgewählten Konfigurationen leistungsstarker Modelle von 36,26 % weniger Tokenverbrauch bei gleichbleibenden Durchschnittswerten. Das Ergebnis bezieht sich auf GPT-4o-basierte Auswertungen und festgelegte Benchmark-Aufgaben; die Arbeit zeigt nicht, dass Fähigkeitsprofile bei anderen Modellen oder realen Workflows ebenso genau abgeleitet werden können.","title":"Kompetenzbewusste Orchestrierung passt die Kommunikation von Agententeams an","topics":[],"translations":[{"api_url":"https://newsverum.com/api/v1/articles/competence-aware-orchestration-adjusts-llm-agent-teams?lang=tr","language":"tr","url":"https://newsverum.com/tr/news/competence-aware-orchestration-adjusts-llm-agent-teams"},{"api_url":"https://newsverum.com/api/v1/articles/competence-aware-orchestration-adjusts-llm-agent-teams?lang=en","language":"en","url":"https://newsverum.com/en/news/competence-aware-orchestration-adjusts-llm-agent-teams"},{"api_url":"https://newsverum.com/api/v1/articles/competence-aware-orchestration-adjusts-llm-agent-teams?lang=ar","language":"ar","url":"https://newsverum.com/ar/news/competence-aware-orchestration-adjusts-llm-agent-teams"},{"api_url":"https://newsverum.com/api/v1/articles/competence-aware-orchestration-adjusts-llm-agent-teams?lang=fr","language":"fr","url":"https://newsverum.com/fr/news/competence-aware-orchestration-adjusts-llm-agent-teams"},{"api_url":"https://newsverum.com/api/v1/articles/competence-aware-orchestration-adjusts-llm-agent-teams?lang=es","language":"es","url":"https://newsverum.com/es/news/competence-aware-orchestration-adjusts-llm-agent-teams"},{"api_url":"https://newsverum.com/api/v1/articles/competence-aware-orchestration-adjusts-llm-agent-teams?lang=de","language":"de","url":"https://newsverum.com/de/news/competence-aware-orchestration-adjusts-llm-agent-teams"},{"api_url":"https://newsverum.com/api/v1/articles/competence-aware-orchestration-adjusts-llm-agent-teams?lang=pt","language":"pt","url":"https://newsverum.com/pt/news/competence-aware-orchestration-adjusts-llm-agent-teams"}],"url":"https://newsverum.com/de/news/competence-aware-orchestration-adjusts-llm-agent-teams"},"version":"1"}