Breaking Down & Testing FIVE LLM Agent Architectures - (Reflexion, LATs, P&E, ReWOO, LLMCompiler)

[@pinkmatter8488]

Your channel has been very valuable today to get me situated on how to get the hang of LLM use. I can now start thinking about project ideas to get some practice. Thank you very much !

[@MekMoney79]

outstanding overview of key the agentic architectures, I learned a ton, prob one of the best out atm - Thanks

[@Kmysiak1]

Bravo. I’ve been looking for something like this all week. Now I need to watch your langgraph videos.

[@AdamLucek]

Glad it was helpful!

[@coolmcdude]

Thank you for this video. Sometimes it’s hard to see what’s happening in agentic frameworks and this video helps explain what’s going on.

[@kenchang3456]

This is really great info, thanks a bunch for sharing. What's really eye-opening is the run times and token counts.

[@PYETech]

That's an amazing work we have here, guys. Cheers to you, bro. Thanks!

[@meetudeshi3520]

Wonderful video with valuable insights!

[@AlexU-o1u]

Good overview. It would be very interesting to see the answer quality benchmarks for these techniques. In a lot of real business cases the time and cost have much less importance than the quality.

[@rodfarm3980]

I'm impressed with the explanations!

[@sanesanyo]

Great work, thanks for this🙏. There is another agentic approach which is called self discovery. Would be cool if you cover that as well 😊.

[@Max_Jean]

Really good break down for folks building,thanks for putting this out

[@tyler-morrison]

This breakdown is insanely helpful 👏 I’ve been working as a Web Engineer for > 10 yrs and recently started learning about AI/ML. I began my career as a self-taught dev in the good ol’ jQuery days, but my lack of CS fundamentals is starting to come back an bite me. These architectural diagrams are incredibly useful for breaking down high-level concepts.

[@AdamLucek]

Glad you found this helpful! Everything I record and share is all self-taught as well, I've got no formal CS background- I just think the topic is interesting and worth sharing!

[@tk0150]

Would you share your slides? So helpful!

[@MEvansMusic]

what is used for scoring?

[@ldelossantos]

Thanks for the explanations!

[@cmthimmaiah]

Very nicely done, thank you for such a good preseentation.

[@kaushilkundalia2197]

Loved this video. Great stuff.

[@caokang4957]

Thank you for sharing! Great summary.

[@hemigwaypl]

Hey! Thanks for clear explanation! Is code available of those agents?

[@GriffinBrown-tq9jz]

Well done! Thank you, sir

[@Jandodev]

We made a 7th with output focused recursive events at my company :)

[@lavamonkeymc]

Question: If I have a data preprocessing agent that has access to around 20 preprocessing tools, what is the best way to go about executing them on a pandas data frame? Do I have the data frame in the State and then pass that input in the function? Does the agent need to have access to that data frame or can we abstract that?

[@AdamLucek]

I imagine it could be abstracted out. A lot of the processing you can do with a langgraph setup similar to these doesn't necessarily need an LLM touch at the computation/function step- could use the LLM for logic based routing to the right node function that is already defined to affect a pre set dataframe

[@xollob]

Hi Adam, great work. I've been struggling trying to evaluate the different agent frameworks, autogen, crewai VRSEN and on and on. langchain etc. seems to be more logical as we can see what's happening and is more predictable. Would it be possible to get the Miro you built for this presentation? Greetings from France.

[@AdamLucek]

Here you go! drive.google.com/file/d/1ESnrIy4c5LPOhNHRnn87Cv7DU_i0-_J9/view?usp=sharing

[@xollob]

@@AdamLucek Thank you so much Adam.

[@lsyang1755]

why is there no ReAct mentioned?

[@ricardoaltamiranomarquez753]

¿Puedes compartir con nosotros tu presentación de Miro?, Great Job

[@AdamLucek]

Here you go! drive.google.com/file/d/1ESnrIy4c5LPOhNHRnn87Cv7DU_i0-_J9/view?usp=sharing

[@ricardoaltamiranomarquez753]

@@AdamLucek thank you very much, you are very good

[@linuszhu]

which one do you prefer for the recommendation

[@AdamLucek]

I would say each have different applications, and are better used as parts of larger agent ecosystems. I.e. taking a reflection based approach to some end validation step would be useful, however a more plan-and-execute style approach to initial generation would likely be a better first step. As with most llm based apps, a lot depends on what data your using, the task/end goal you want, and your tolerance of processing time. Would more so apply the general concepts here rather than see them as strict end solutions 😁

[@genXstream]

Which would you say is more crucial to analyzing the "correctness" of the language agent tree search result: "blah blah blah" or "yada yada yada"?

[@AdamLucek]

Im more partial to yada yada yada, but I can see the benefits of blah blah blah. Really comes down to your use case and desired blah to yada ratio

[@JEffigy]

Hey can you please share the miro board link? Or drop it into a high res pdf? AWESOME work btw 👍👍👍

[@AdamLucek]

Here you go! drive.google.com/file/d/1ESnrIy4c5LPOhNHRnn87Cv7DU_i0-_J9/view?usp=sharing

[@ShaunPrince]

The volume is super low on this, compared to every other video I have watched today. Consider trying to hit the 0db mark while you speak normally, in your screen capturing app. You don't seem like someone that gets excited or screams, so as long as you just act like yourself, the 0db setting should be perfect for you. Good luck!

[@AdamLucek]

Thanks for the feedback! Trying to tune the levels right to not pick up the construction happening outside my window mainly 😂

[@matthewpublikum3114]

Where's the code? It would be nice to know what is the smallest LLM capable of doing the planner/task decomposition and verification.

[@AdamLucek]

The code comes from LangChain's series on LangGraph, linked in the description. Here's a direct link to their repo github.com/langchain-ai/langgraph/tree/main/examples

[@LouvoresPauloRicardo]

Great video! Could you share the code?

[@AdamLucek]

Thanks! The code comes from LangChain's series on LangGraph, linked in the description. Here's a direct link to their repo github.com/langchain-ai/langgraph/tree/main/examples

[@utkarshgarg8783]

Explanation of LATS is wrong. You only pick best nodes during simulation stage. During selection in mcts, you using uct algo to control exploration and exploitation.

[@AdamLucek]

Thanks for the clarification!

[@niftylius]

Hello

[@sharannagarajan4089]

AlL of them suck

[@readmarketings9061]

Do you have better solution?

[@missigno42]

Why?