🏆 AML Cycle 2 results are live! 💥 • 1M+ cross-platform impressions • 10M+ cumulative website clicks • 402 task submissions • Three tracks: text, code and multimodal memory This cycle brought together teams from across the global AI community, including teams from Alibaba Cloud DMS, Shopee, OPPO, KT and OceanBase—alongside university researchers, memory startups and independent developers. Explore the full results:
How should we evaluate image memory in AI agents?
The second cycle of the AML (Agent Memory Leaderboard) competition drew 402 task submissions across three tracks — text, code and multimodal memory — and generated more than 1 million cross-platform impressions and over 10 million cumulative website clicks, according to the organizers' published results. Participating teams included Alibaba Cloud DMS, Shopee, OPPO, KT and OceanBase, alongside university researchers, memory startups and independent developers. The cycle's headline question, how to evaluate image memory in AI agents, reflects the benchmark's expansion into multimodal agent memory.
Benchmark agent memory on separate text, code and multimodal tracks rather than one aggregate score, as AML Cycle 2 did across 402 task submissions.
more in playbook: Evals and testing for LLM appsRun your AI side-project on zahid.host
EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.