What the field is saying.

My preferred definition of an LLM agent is something that runs tools in a loop to achieve a goal.

Simon Willison · Designing agentic loops

A short, sharp guide to tool choice and stop conditions from one of the clearest writers in the field.

Consistently, the most successful implementations use simple, composable patterns rather than complex frameworks.

Anthropic · Building effective agents

The canonical workflow-versus-agent framing, with the simple-loop-first advice every builder should start from.

We explore the use of LLMs to generate both reasoning traces and task-specific actions in an interleaved manner.

Yao et al. · ReAct

The paper that made the think, act, observe cycle legible as the core shape of modern agents.