A language model operating in a loop with tools, memory, and an environment, taking multi-step actions toward a goal rather than returning a single response.
Tensions
The 2026 consensus (Luo Fuli) is that agent capability is now bound by post-training, not pre-training: the base model gap has largely closed, so the differentiation moves to how well a team does RL on agents and how fast it can rewrite agent-centric infra. Yet Yao Shunyu notes that outside agentic coding, no agent scenario has yet formed a real data flywheel, so the durable advantage still sits on the model side.