Tencent's Hy3 drops the license restrictions that blocked EU and U.K. deployments, cuts hallucination rates in half, and runs ...

By registering the LongCat-2.0 repository under the open-source MIT License, Meituan positions the architecture with maximum ...

DSpark can make decoding faster, but acceptance quality still determines how much speed the system actually realizes.

Louis Rosenberg earned his PhD from Stanford University, was a professor at California State University (Cal Poly) and has ...

General-purpose models struggle with messy, industry-specific data. A three-layer AI stack from Trunk Tools cut document ...

Shipping an agent to production isn’t just a harder version of shipping a generative AI chatbot. Agentic production is a ...

AI compressed the build. Fundamentals matter more, not less, and the product funnel is now where engineers earn their keep.

AI has made it easy to ship code faster — but incidents-to-PR ratio is up 242.7% and bugs per developer up 54%. Here's what a ...

Xiaomi's HarnessX autonomously rewrites AI agent harnesses mid-execution, delivering +14.5% avg performance gains — and +44% ...

Sol and Terra set new high benchmark scores, while Luna performs near GPT-5.5 levels on several tests despite being ...

NUS researchers' MRAgent framework reduces LLM agent memory retrieval to 118K tokens per query — vs. 3.26M for LangMem — ...

Real environments can't inject edge cases on demand. Alibaba's Qwen-AgentWorld simulates them — and outperformed ...