AI代理與工作流程之間的譜系:為何LLM代理大多是圖形結構 (2025-2026觀點)

AI代理與工作流程之間的譜系:為何LLM代理大多是圖形結構 (2025-2026觀點)

Hacker News·

本文分析了當前AI代理的現況,指出大多數現代「AI代理」本質上是包含動作、LLM呼叫和工具執行的定向圖,並具備路由邏輯和共享狀態。文章提出了2025-2026年的實用共識,將AI代理視為一個譜系,從預定義的DAG到由LLM控制的開放式規劃。

AI Tips, Tech & Gaming | Simple Guides and Smart Tools

Discover practical AI tips, tech guides, and gaming tricks. Simple tutorials, smart tools, and useful advice to improve your digital experience.

Jan 16, 2026

AI Agents vs Workflows: Why LLM Agents Are Mostly Graphs (2025–2026 Perspective)

AI agents: less magic, more graphs

Image

You’re spot on: most modern “AI agents” boil down to directed graphs, often with cycles.

Common structure:

Nodes: actions, LLM calls, tool executions

Edges: routing logic (conditional or LLM-decided)

Shared state: memory/context

Loops/feedback: what makes it feel non-linear

Add:

LLM-based routing

cycles (reflection, retries)

➡️ and a boring DAG suddenly feels agentic.

That’s why frameworks like LangGraph are explicit about this abstraction.

Why the Hacker News frustration makes sense

On HN, “agent” is criticized as a marketing label:
anything with ≥1 tool call + a loop gets branded as an agent,
even when execution is mostly predefined.

Many production “agents” are actually quite deterministic.

The 2025–2026 practical consensus: a spectrum

Fully predefined DAG

LLM used for fixed tasks

Highly predictable, low cost

→ Zapier/n8n + LLM node, classic RAG

Mostly structured

LLM decides branches, retries, tool choice within guardrails

Bounded loops and planning

→ Used by many real products
→ Andrew Ng: agentic systems

LLM controls its own process

Open-ended planning and self-correction

Rare in production at scale today

The pragmatic definition

Many experienced engineers say:

“If the DAG is largely steered by the LLM at runtime, it’s agentic.”

The winning approach:
➡️ start with workflows
➡️ add agentic behavior where needed
➡️ scale autonomy as models improve and costs drop

Image

AI Agents vs Workflows: Why LLM Agents Are Mostly Graphs (2025–2026 Perspective)

AI agents: less magic, more graphs You’re spot on: most modern “AI agents” boil down to directed graphs , often with cycles. Common structur...

Image

Image

Search This Blog

About Me

Report Abuse

Blog Archive

Hacker News

相關文章

  1. LLM 代理工具使用的演進:從單一工具調用到多工具編排

    Rohan Paul · 19 天前

  2. 從零到一:AI代理與代理模式

    3 個月前

  3. 構建可靠的AI代理

    3 個月前

  4. 大語言模型作為淺層電路的巨型查找表

    Lesswrong · 大約 1 個月前

  5. 代理技能

    3 個月前