asynchronous-rl

Tag

Cards List
#asynchronous-rl

@VukRosic99: How Is GLM 5.2 Trained? Tsinghua's Async RL Paper Explained The paper from Tsinghua University replaces GRPO's wait-for…

X AI KOLs Timeline · 2026-07-11 Cached

This paper from Tsinghua University introduces Single-rollout Asynchronous Optimization (SAO) for reinforcement learning post-training of LLMs. SAO replaces batch-based GRPO with single-rollout asynchronous training to reduce idle GPU time and improve stability, and it was used to train the GLM-5.2 model (750B-A40B), achieving state-of-the-art results on agentic coding and reasoning benchmarks.

0 favorites 0 likes
#asynchronous-rl

Z.ai's Stable Asynchronous RL (13 minute read)

TLDR AI · 2026-07-10 Cached

The paper introduces Single-rollout Asynchronous Optimization (SAO) to address stability and off-policy challenges in asynchronous RL for LLM post-training, and demonstrates that SAO consistently outperforms GRPO on agentic coding and reasoning benchmarks.

0 favorites 0 likes
#asynchronous-rl

@Chengxing_Xie: Tsinghua has introduced SAO, an algorithm designed to address the off-policy drift and stability challenges that arise …

X AI KOLs Timeline · 2026-07-09 Cached

Tsinghua's SAO algorithm addresses stability and off-policy drift in asynchronous reinforcement learning for LLMs, achieving consistent improvements over GRPO on agentic coding and reasoning benchmarks, and is used to train the GLM-5.2 model.

0 favorites 0 likes
#asynchronous-rl

@eliebakouch: every infra piece you need to know to do RL on GLM-5 https://primeintellect.ai/blog/rl-at-1t-scale…

X AI KOLs Timeline · 2026-06-23 Cached

Prime Intellect releases prime-rl v0.6.0, enabling efficient reinforcement learning at trillion-parameter scale on large Mixture-of-Experts models, with sub-5-minute step times and optimizations for asynchronous RL.

0 favorites 0 likes
#asynchronous-rl

@vivek_2332: new blog: weight synchronization in async rl. weight sync has gotten a lot faster lately, sub-2s even on frontier model…

X AI KOLs Timeline · 2026-06-18 Cached

A blog post exploring weight synchronization techniques in asynchronous reinforcement learning, covering transport and payload trade-offs across frameworks.

0 favorites 0 likes
#asynchronous-rl

@_djdumpling: Luke is one of the best people when it comes to RL infra, definitely worth reading!

X AI KOLs Timeline · 2026-06-01 Cached

Luke J. Huang's new blog post surveys asynchronous reinforcement learning theory and infrastructure across 8 open-weight frontier labs, addressing algorithmic techniques and systems fixes for train-inference mismatch.

0 favorites 0 likes
← Back to home

Submit Feedback