16. Agents¶
Models that pursue goals through iterative action, not single replies. Children describe the agent loop: goal → task → plan → action → observation → feedback, powered by tool use and memory, situated in an environment, optionally with a human in the loop, in single- or multi-agent configurations. Note the deliberate echo of reinforcement learning's vocabulary — an agent is RL's action/observation loop generalized to LLMs + tools.
Children¶
- agent
- goal
- task
- plan
- action
- observation
- tool use
- memory
- environment
- feedback loop
- human-in-the-loop
- single-agent workflow
- multi-agent workflow
Examples¶
- OpenAI Deep Research
- Claude Code
- Devin-like coding agents
- OpenClaw — self-hosted personal agent runtime (LLM + tools + memory + channels + cron + real accounts)
Related¶
- Machine Learning — reinforcement learning's agent/environment loop
- Tools, Skills & Protocols — what agents act with
- Reasoning & Test-Time Compute — planning and reflection
- Knowledge & Memory — agent memory