Updated just now
Related News
Nov 10, 2026
Google's MKA benchmark tests AI agents on 200 private professional tasks; a separate set of 10 public tasks is available for inspection
Google DeepMind's new Multimodal Knowledge Agent benchmark evaluates AI agents on 200 private tasks requiring visual analysis of complex professional files like architectural blueprints and engineering schematics. While the benchmark's headline scores are based on these private evaluations, only 10 sample tasks are publicly available for inspection. The benchmark uses weighted criteria where harder 'Climb' criteria measure advanced performance, and costs reported by Artificial Analysis exclude judge calls, limiting direct workplace cost comparisons.
AI benchmarksAI agentsGoogle DeepMind
Nov 8, 2026
ReproBridge preprint reports lower API costs for reusable ML artifacts
A selected-task study packages code, setup, launchers and a guide. Its reported API savings exclude construction and other costs; an evidence-and-budget record shows what to inspect before reuse.
AI researchAI agentsMachine learning
Nov 7, 2026
OpenAI Agents SDK preview separates local profiles from portable checkpoints
Alpha.6 adds LocalStorage and expands SessionState recovery. Its pinned guide keeps runtime compatibility, current tool authority and unknown external effects as separate checks.
AI agentsOpenAIDeveloper tools