Search

10 results on this page

New Benchmark Tests Whether AI Can Draw Geometry

New Benchmark Tests Whether AI Can Draw Geometry

Researchers introduce an open-source benchmark separating olympiad geometry solving from accurate diagram construction. Across 954 problems, current foundation models achieved only a 36.14% average diagram compilation success rate, revealing a substantial gap between mathematical reasoning and faithful visual construction.

ArXiv AIResearch23h ago#geometry-reasoning#benchmark#asymptote
KnowledgeForge Turns ITSM Tickets Into Knowledge

KnowledgeForge Turns ITSM Tickets Into Knowledge

KnowledgeForge converts resolved ITSM incident tickets into new knowledge base articles and continuously curates existing content. Its multi-tenant, closed-loop pipeline uses Amazon Bedrock, Amazon S3 Vectors, and AWS Step Functions for deduplication, quality scoring, and content improvement.

AWS Machine Learning BlogOfficial1d ago#itsm#knowledge-base#closed-loop
Page 3