A detailed reverse-engineering of Claude Code's agent architecture, revealing how a single-threaded master loop with flat message history, structured tool interfaces, async steering, and TODO-based planning delivers controllable autonomy without multi-agent complexity.

Google's comprehensive whitepaper distinguishing agents from plain models, explaining how tools, orchestration layers, and cognitive architectures combine to create capable AI agents.

Lilian Weng's seminal deep-dive into the architecture of LLM-based autonomous agents, covering planning (CoT, ToT, self-reflection), memory systems (sensory, short-term, long-term), and tool use as the three pillars of agent design.