LLM Agents Are Simply Graph – Tutorial for Dummies

Post by zh2408 » Thu, Mar 20, 2025, 2:36 AM UTC

jwpapi wrote: post #38

campbel wrote: post #7

I follow Mr. Huang, read/watch his content and also plan to use PocketFlow in some cases. A preamble, because I don't agree with this assessment. I think agents as nodes in a DAG workflow is _an_ implementation of an agentic system, but is not the systems I most often interact with (e.g. Cursor, Claude + MCP). Agentic systems can be simply the LLM + prompting + tools[1]. LLMs are more than capable (especially chain-o…

I have to agree this is a bit too simple for being anything of substance. That is not what really agentic means. This is basically implementing ChatGPT into Zapier. When you work with agentic LLMs you should worry about prompt chaining, parallel execution, deciding points, loops and more of these complex decisions. People who didn’t know what’s in first article shouldn’t use Pocketflow and go with N8N or even Zapier.

Post by achierius » Thu, Mar 20, 2025, 2:39 AM UTC

throwaway7783 wrote: post #40

yed wrote: post #18

Earlier quoted context omitted.

No I'm referring to the newest generation of agentic models one of which I linked to. These are not fully released but it is where the newest generation of research is headed.

Operator/Computer Use is a bridge until we no longer need any tools at all

Post by windsignaling » Thu, Mar 20, 2025, 2:41 AM UTC

godelski wrote: post #32

zh2408 wrote: post #10

Earlier quoted context omitted.

Hey, sorry for the confusion. This tutorial is focusing on the low-level internals of how agents are implemented—much like how intelligent large language models still boil down to matrix multiplications at their core.

> This tutorial is focusing on the low-level internals of how agents are implemented We have very different definitions of what "low-level" means. Exact opposites in fact. "Low-level" means in the inner workings. Like a low-level language is assembly (some consider C low-level but this is debatable), whereas Python would be high-level. I don't think this tutorial is "near the metal" of LLMs nor do I think it should b…

Post by godelski » Thu, Mar 20, 2025, 3:55 AM UTC

windsignaling wrote: post #45

godelski wrote: post #32

Earlier quoted context omitted.

> This tutorial is focusing on the low-level internals of how agents are implemented We have very different definitions of what "low-level" means. Exact opposites in fact. "Low-level" means in the inner workings. Like a low-level language is assembly (some consider C low-level but this is debatable), whereas Python would be high-level. I don't think this tutorial is "near the metal" of LLMs nor do I think it should b…

I think "low-level" is relative to what's being discussed. Low-level for LLMs would have to do with how transformer layers are implemented (self-attention layer, layer norms, etc.) whereas low-level for agents would be the graph structure. Although I personally don't think the graph implementation for agents is necessarily as established or widely standardized, it's helpful to know about why such an implementation wa…

  > You can say that about anything.

Post by campbel » Thu, Mar 20, 2025, 4:25 AM UTC

zh2408 wrote: post #46

campbel wrote: post #42

Earlier quoted context omitted.

This link is also referring to the nodes as agents. So its a system of agents interacting to product an outcome. I'm not saying this system is bad, just that I think it deserves another name rather than calling the whole system an "Agent". It's many agents working in a coordinated fashion.

No. It's not many agents in the workflow. It's not an agent per node. The whole workflow and the Runner class is for one agent. Check out this line: https://github.com/openai/openai-agents-python/blob/48ff99bb... A single `run_agent` is implemented based on the Runner class and workflow. So usually the workflow is for one agent (unless there is handoff).