LLM Watch

LLM Watch

Home
Deep Dives
Vibe Coding 101
State of AI Agents
Archive
About
The Week in AI Agents: Papers You Should Know About
From ReAct to Pre-Act and Strategy-Augmented AI Planning
 • 
Pascal Biese
🧬 Google's AI Evolution Breakthrough
Learn about AlphaEvolve, Qwen3 and how Reasoning Models omit their "thoughts"
AlphaEvolve: Google DeepMind's Latest Breakthrough Success
A Coding Agent for Scientific and Algorithmic Discovery
 • 
Pascal Biese
Agent Watch: The Week in AI Agents
Papers you should know about
 • 
Pascal Biese
NVIDIA's LLamaTron Moment
Learn about Llama-Nemotron, Absolute Zero and how to rethink memory in AI
Llama-Nemotron: NVIDIA's Foundation Model for Agentic AI
A New Generation of Efficient Reasoning Models
 • 
Pascal Biese
The Week in AI Agents: Papers You Should Know About
Stay ahead of the curve with LLM Watch
 • 
Pascal Biese
📉 May the Best Cheater Win
Learn about Qwen3, ThinkPRM, and the Leaderboard Illusion

April 2025

ThinkPRM: More Than Just Chain-of-Thought (CoT 2.0)
AI models that verify reasoning steps with Advanced Chain-of-Thought
 • 
Pascal Biese
Multi-Agent Failure: What It Is and How to Prevent It
A Deep Dive into Failure Modes and System Design
 • 
Pascal Biese
The Week in AI Agents: Papers You Should Know About
Keeping up with AI doesn't have to be tedious
 • 
Pascal Biese
🤗 Reinforcement Learning Without Human Feedback
The Reinforcement Learning hype just won't stop - another week full of RL papers
1
© 2025 Pascal Biese
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture