concept · created Jun 4, 2026 · updated Jul 12, 2026

llm-agent

#llm-agent#agent-engineering#mental-model#harness

The LLM-powered autonomous agent — the canonical anatomy from Lilian Weng‘s 2023 survey (2026-06-04-llm-powered-autonomous-agents): an LLM acting as the agent’s “brain” (controller), wrapped by three components.

ComponentWhat it doesWiki page
PlanningDecompose the task into subgoals; reflect on and correct past actionstask-decomposition + self-reflection
MemoryHold the working context (short-term) and recall facts/experience over time (long-term)agent-memory + maximum-inner-product-search
Tool useCall external APIs for what the weights don’t contain — current info, code execution, proprietary datatool-use

The original overview figure puts Agent at the center with four spokes — Tools (Calendar(), Calculator(), CodeInterpreter(), Search(), …), Action, Memory (short-term / long-term), and Planning (Reflection, Self-critics, Chain of thoughts, Subgoal decomposition). That four-box picture became the default mental model for “what an agent is”.

Why this page is the ancestor, not just another concept

This wiki’s center of gravity is 2026-era agent engineering — harnesses, context engineering, verifier loops. Almost all of that vocabulary descends from this 2023 decomposition. The mapping, made explicit so the lineage is visible:

Weng 2023 (this page)2026 wiki descendant
LLM brain + perceive/act cycleagent-loop — the ~20-line ReAct loop (react)
Planning → subgoal decompositiontask-decomposition, plan-mode
Planning → reflection / self-criticsself-reflectionralph-wiggum-loop, verifier-loop
Short-term memory = in-context learningcontext-engineering (working memory)
Long-term memory = external vector storeagent-memory, maximum-inner-product-search
Tool use (“knowing when & how”)tool-useagent-computer-interface, model-context-protocol
Chain of Thought as a planning aidchain-of-thoughtreasoning-models

So the modern stack didn’t replace this frame — it industrialized each box. The harness wraps the loop; context engineering manages the memory budget; ACI/MCP formalize tool use; verifier loops operationalize self-reflection.

What 2026 sources changed

  • Memory. Weng’s default was “long-term memory = vector store + RAG”. The 2026 agent-memory sources argue markdown + simple retrieval beats a vector DB at small/medium scale, and split memory four ways (working / procedural / episodic / semantic). Notably, Weng’s human taxonomy already contained episodic + semantic + procedural — the 2026 frame essentially re-applied the human taxonomy to file-backed engineering instead of to a vector store.
  • Planning. Reflection here is prompt-/SFT-level (Reflexion, Chain of Hindsight). The 2026 descendants externalize it: agents review each other and loop until verifiers pass (ralph-wiggum-loop).
  • Reliability. Weng’s third “challenge” — the natural-language interface is unreliable, so most agent code is output parsing — got addressed by structured tool calling and prompt-cache-shaped harnesses (prompt-caching), not by the problem disappearing.

Weng’s own 2026 revision — agent anatomy → harness anatomy

The author herself updated the frame three years on. 2026-07-07-harness-engineering-self-improvement (Jul 2026) defines the harness as the successor anatomy: everything the 2023 three-component frame had (planning, memory, tool use around an LLM brain), plus workflow design, evaluation, permission controls, and persistent state management — “closer to runtime and OS design than prompt templates”. Two things changed between the frames:

  • The unit of engineering moved from components to code. The 2023 anatomy names capabilities; the 2026 harness is a program — “code that programs how prompts, tool calls, subagents, control flow, memory, and workflow logic work together”. That makes the whole anatomy an optimization target (recursive-self-improvement, meta-harness), which the 2023 frame never contemplated.
  • Evaluation and permissions joined the anatomy. The 2023 survey treated evaluation as an external research concern; the 2026 frame builds the evaluator (and its placement outside the self-improvement loop) into the system definition itself.

So this page’s lineage table gains a final row: the 2023 anatomy’s descendant is not just each industrialized box — it’s the harness as a whole.

The proof-of-concept era it captured

Written at the AutoGPT / BabyAGI / GPT-Engineer peak. Weng’s verdict on those demos — “a lot of code in AutoGPT is about format parsing” — was the early signal that the harness around the model, not the model alone, was where the engineering would go (harness). Those POCs aren’t their own pages yet; they’re discussed on 2026-06-04-llm-powered-autonomous-agents and tool-use.

Referenced by 8

2026-06-04-llm-powered-autonomous-agents 2026-07-07-harness-engineering-self-improvement agent-loop maximum-inner-product-search self-reflection task-decomposition tool-use lilian-weng
esc