Tag

#reinforcement-learning

3 stories.

$A figure from the paper \\\"Know What You Don’t Know: Agentic Data Synthesis by Evolving Generation Space for Closed-L\\\".$ How it worksAI Researchers Build a System That Learns What It Doesn't Know to Make Better Training DataHerald of AIFigure: Yang et al., arXiv:2610.12593, CC BY 4.0

AI Researchers Build a System That Learns What It Doesn't Know to Make Better Training Data

A new multi-agent framework helps AI systems generate smarter training data by identifying and fixing their own weaknesses.

Oct 13, 2026

Detailed view of GeForce RTX graphics card inside a computer, showcasing modern technology.

How it worksAlibaba's QwenGyre Makes Training Long-Running AI Agents Much FasterHerald of AI

Alibaba's QwenGyre Makes Training Long-Running AI Agents Much Faster

A new elastic reinforcement learning system lets AI coding agents run for hours while still training efficiently on expensive GPU hardware.

Oct 13, 2026

Hand writing complex math equations on a blackboard in a classroom setting.

How it worksMagicBeanStalk synthesizes better training data to boost AI reasoningHerald of AI

MagicBeanStalk synthesizes better training data to boost AI reasoning

A new method grows hard math and finance problems from just a few examples, helping gpt-oss-120b and DeepSeek v4 Flash improve by nearly 9 points.

Oct 13, 2026