Meta’s DreamGym framework trains AI agents in a simulated world to cut reinforcement learning costs

The new framework sidesteps costly and risky real-world rollouts by generating synthetic training data, making powerful ...

Google’s new AI training method helps small models tackle complex reasoning

Google's SRL framework provides a step-by-step "curriculum" that makes LLMs more reliable for complex reasoning tasks.

Ai2 releases Olmo 3 open models, rivaling Meta, DeepSeek and others on performance and efficiency

The Allen Institute for AI (Ai2) unveiled Olmo 3, a new generation of open language models that it says outperforms rivals ...

Meta’s SPICE framework pushes AI toward self-learning without human supervision

The new reinforcement learning system lets large language models challenge and improve themselves using real-world data ...
Tech Xplore on MSN

The cost of thinking: Reasoning models share aspects of information processing with human brains

Large language models (LLMs) like ChatGPT can write an essay or plan a menu almost instantly. But until recently, it was also ...
InfoWorld

Are large language models wrong for coding?

The rise of large language models (LLMs) such as GPT-4, with their ability to generate highly fluent, confident text has been remarkable, as I’ve written. Sadly, so has the hype: Microsoft researchers ...
EurekAlert!

Reinforcement learning world models for catalyst surface reconstruction: state-of-the-art review

This work presents an AI-based world model framework that simulates atomic-level reconstructions in catalyst surfaces under dynamic conditions. Focusing on AgPd nanoalloys, it leverages Dreamer-style ...
Microsoft

With reinforcement learning, Microsoft brings a new class of AI solutions to customers

Someone looking to book a vacation online today might have very different preferences than they did before the COVID-19 pandemic. Instead of flying to an exotic beach, they might feel more comfortable ...