JUST IN: Q* has been solved.
This is a AI post classified by Jev as AI research (a tool drop), kept by the AI Radar because it carries real work, not commentary.
JUST IN: Q* has been solved. Welcome to the frontier of RL scaling. KL-Regularized Policy Optimization for Critic-Free Agentic Reinforcement Learning https://github.com/yifanzhang-pro/KLPO From GPO, SPPO, and RPG to BPO and Score Centering, we have finally arrived at the grand finale of RL science and Q*.
Posted by Yifan Zhang (22.7k followers) 2 h ago · 702 likes · 113.5k views · view the original post on X. Kept by the AI Radar as AI research. Tools mentioned: klpo, flashreinforce.
More AI work like this
- “Reinforcement Learning for Real-Time Vision-Language-Action Policies” — @askalphaxiv
- Impressive paper on building recursive self-improving agent harnesses. — @dair_ai
- 这篇笔记详细的介绍了DeepSeek-V4.1-Flash 背后的跨层 KV 共享：YOCO，以及相关的变种架构 — @qingke_ai
- 这篇笔记详细的介绍了DeepSeek-V4.1-Flash 背后的跨层 KV 共享：YOCO，以及相关的变种架构 — @qingke_ai
- OpenAI researcher "Alisa Liu" had 57 interviews before joining OpenAI, and then She… — @0x0SojalSec
- UPDATE! — @BrianRoemmele
- HerHealthEval tests clinical LLMs across English, French, Arabic in six registers. — @biogerontology
- "JEPA-Anything: Learning Predictive Models across Different Worlds" — @askalphaxiv
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 35.4k posts from 5k X accounts over the last 14 days, 1.5k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-21 03:27 UTC. Full method.