BLOG
Tencent Hunyuan open-sources Hy Memory 2.0: the 3B-active writer model Hy-Memory-30B-A3B, the hy-memory SDK, and local-first MemHub; a 55.49 macro average over four harnesses edges out Opus 5.
Most multi-agent systems are still queues. This roadmap redraws them as graphs: nodes do work, edges move data, independent nodes run in parallel, and results converge only on real dependencies.
Uber's Legal Redlining Agent lives inside Microsoft Word: four iterations (RAG, lawyer feedback, tone, agentic modifications) cut average review time over 20% with 91% decision accuracy.
Code2Skill turns 19,769 GitHub repos into 1,006,822 verified skill records; retrieved skills lift macro-average 11.7% and beat trajectory-derived banks on all seven shared benchmarks.
Meta distills compliance expertise into 200+ structured files, splits what the agent knows from how it reasons via recipes, and compiles expert fixes into regression-tested edits, no model retraining.
As an Amazon Associate, we earn from qualifying purchases.
