Library Progress

Generated Files

llm-course/home

Topics

MDComputer & Python Foundations7 files MDMathematics11 files MDMachine Learning8 files MDNeural Networks12 files MDNLP7 files MDTokenization12 files MDEmbeddings7 files MDPositional Information6 files MDAttention12 files MDMulti-Head Attention6 files MDTransformer10 files MDLanguage Modeling6 files MDText Generation7 files MDStopping Generation6 files MDLLM Architecture9 files MDContext Window6 files MDLLM Training15 files MDBuild a Small LLM10 files MDModel Precision5 files MDQuantization14 files MDGPU & Memory7 files MDKV Cache5 files MDFine-Tuning6 files MDLoRA7 files MDAlignment6 files MDRAG12 files MDVector Search10 files MDFunction Calling7 files MDAgents8 files MDInference9 files MDInference Optimization4 files MDDistributed Training7 files MDMixture of Experts6 files MDMultimodal LLMs7 files MDReasoning Models6 files MDEvaluation10 files MDLLM Systems9 files MDLLM Research10 files

Course progress

0%

0% of 38 sections

LLM Learning Hub

workspace/llm-course/home

BASE

Planning

Planning is the agent's ability to decompose a complex goal into a sequence of sub-tasks before execution, improving coherence and reducing errors in multi-step problems.

What is Planning?

Planning is the agent's ability to decompose a complex goal into a sequence of sub-tasks before execution, improving coherence and reducing errors in multi-step problems.

Planning is the agent's ability to decompose a complex goal into a sequence of sub-tasks before execution, improving coherence and reducing errors in multi-step problems.

Where is it used?

Tree-of-Thoughts, ReWOO, and LangGraph `Plan-and-Execute` agents plan upfront; OpenAI o1 and Claude internally reason through plans before producing a final answer.

How to build it

Prompt the LLM with `"Break this task into numbered sub-tasks: {goal}"`, parse the list, then iterate executing each sub-task with its own tool-calling sub-loop.