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.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
Why it matters
A game AI agentAn 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.Full definition → that parses intent and reads the scene rather than matching scripted phrases, with the compute cost that keeps it off mobile. A usable reference point for anyone putting an LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition → agent inside a latency budget.
articleTencent Unveils Full Stack Embodied Intelligence Solution At Waic 2026Tencent
articleTencent Announces Global Rollout Of Scenario Based Ai Capabilities To Accelerate Industrial EfficiencyTencent
videoLocal Agentic Theory For Mobile Games — Shafik Quoraishee & Joanne Song, The New York TimesAI Engineer