ddiruscio/logseq
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Recovered after rebase

Browse Source
This commit is contained in:
Davide Di Ruscio
2025-06-22 20:36:12 +02:00
parent f27d0bc951
commit 33f6de7df9
25 changed files with 844 additions and 422 deletions
Download Patch File Download Diff File Expand all files Collapse all files
pages/Agentic AI.md
+7 -5
View File
@@ -1,11 +1,13 @@
icon:: 🧠
- ***Agentic AI***: Systems that can *plan*, *reason*, and *take action* to *accomplish tasks* with *minimal human intervention*.
- AI agents extend the capabilities of LLMs with respect to the following dimensions:
- *Integrating memory*, to retain and recall information across interactions
- *Tool use*, to utilize external tools, APIs, and databases
- *Decision-making*, to plan and execute multi-step workflows
- AI agents will continue to refine the ability to *reason*, *plan*, and *act*.
- Certainly! Here's the revised text with grammatical corrections:
- ***Agentic AI***: Systems that can *plan*, *reason*, and *take action* to *accomplish tasks* with *minimal human intervention*.
- - AI agents extend the capabilities of LLMs in the following dimensions:
- - *Integrating memory* to retain and recall information across interactions
- - *Tool use* to utilize external tools, APIs, and databases
- - *Decision-making* to plan and execute multi-step workflows
- - AI agents will continue to refine their ability to *reason*, *plan*, and *act*.
- The **development of agentic-based AI** is a natural progression from *statistical modeling* to *deep learning* and now to *reasoning-based systems*
- This evolution marks a shift from predictive models to autonomous systems capable of dynamic decision-making.
- The **main challenges with raw LLMs** are the following: