Agentic AI – Hype or the Next Step in AI Evolution?

Gradient Descent - Podcast about AI and Data

Apr 12, 2025•41 min•Season 1Ep. 3

--:--

Listen in podcast apps:

Apple Podcasts

Spotify

Download

Listen to this episode in Metacast mobile app

Don't just listen to podcasts. Learn from them with transcripts, summaries, and chapters for every episode. Skim, search, and bookmark insights. Learn more

Episode description

Let’s dive into Agentic AI, guided by the "Cognitive Architectures for Language Agents" (CoALA) paper. What defines an agentic system? How does it plan, leverage memory, and execute tasks? We explore semantic, episodic, and procedural memory, discuss decision-making loops, and examine how agents integrate with external APIs (think LangGraph). Learn how AI tackles complex automation — from code generation to playing Minecraft — and why designing robust action spaces is key to scaling systems. We also touch on challenges like memory updates and the ethics of agentic AI. Get actionable insight…

🔗 Links to the CoALA paper, LangGraph, and more in the description.

🔔 Subscribe to stay updated with Gradient Descent!

Listen on:

• ⁠YouTube⁠: https://youtube.com/@WisecubeAI/podcasts

• ⁠Apple Podcast⁠: https://apple.co/4kPMxZf

• ⁠Spotify⁠: https://open.spotify.com/show/1nG58pwg2Dv6oAhCTzab55

• ⁠Amazon Music⁠: https://bit.ly/4izpdO2

Mentioned Materials:

• Cognitive Architectures for Language Agents (CoALA) - https://arxiv.org/abs/2309.02427

• Memory for agents - https://blog.langchain.dev/memory-for-agents/

• LangChain - https://python.langchain.com/docs/introduction/

• LangGraph - https://langchain-ai.github.io/langgraph/