← Back to Model Beat
Research·Aug 28·all news from August 28, 2026

Terminal-Bench-Science: Evaluating AI agents on scientific research workflows

Covered by 1 source

Related stories

ResearchMetaRoCE: A New RDMA Transport Built for AI-Scale EthernetAug 24 · 2 sourcesResearchGoogle's WikiSkill gives AI agents a persistent memory of past mistakes to sharpen future performanceAug 28 · 2 sourcesResearchFederal Appeals Court Blocks Charge Over Private Possession of AI-Generated Child Sexual Abuse ImagesAug 30 · 5 sourcesResearchAutomated researchers can reliably mitigate alignment failuresAug 28 · 2 sources