• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
• context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
• subagent — A separate agent spawned by another to do one scoped piece of work in its own context, returning only the result.
• mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.

AgentX measures inference the way agents actually load it — long prefill, KV-cache reuse, bursty concurrency — making it a better proxy for real serving cost than single-turn benchmarks.

• articleHow Generative Recommenders Are Redefining RecSys at Scale
• articleDeveloping NVIDIA Holoscan Applications with CLI, Skills, and AI Coding Agents
• articleHow AI Coding Agents Can Unlock Materials Simulation with NVIDIA ALCHEMI Toolkit
• articleLessons From the Leaderboard: What 5,000+ Kagglers Taught Us About Improving AI Reasoning

• articleHow NVIDIA Groq 3 LPX Unlocks Ultrafast Interactivity at Long Context on NVIDIA Vera RubinTanya Lenz
• articleAgentX: an open benchmark for million-token agentic inferenceSemiAnalysis
• articleNVIDIA AVO Reaches 100% on ARC-AGI-3, Demonstrating a Frontier-Level General-Purpose Architecture for Long-Horizon Autonomous AgentsTanya Lenz

Checking sign-in…

Loading comments…