Infini-AI-Lab on X: "We’re excited to release 𝐀𝐬𝐭𝐫𝐚𝐅𝐥𝐨𝐰, an open-source, dataflow-oriented RL system for training multi-agentic and multi-policy LLMs. 🚀 Built for scalable, flexible, and efficient agent RL, AstraFlow natively enables: ⚡ 𝟐.𝟕× 𝐟𝐚𝐬𝐭𝐞𝐫 𝐦𝐮𝐥𝐭𝐢-𝐩𝐨𝐥𝐢𝐜𝐲 https://t.co/JVthM8iHur" / X

To view keyboard shortcuts, press question mark View keyboard shortcuts Home Explore Notifications Chat Grok Premium Money Bookmarks Creator Studio Articles Profile More Post christina @luoluo Post See new posts Conversation Infini-AI-Lab @InfiniAILab We’re excited to release 𝐀𝐬𝐭𝐫𝐚𝐅𝐥𝐨𝐰, an open-source, dataflow-oriented RL system for training multi-agentic and multi-policy LLMs. Built for scalable, flexible, and efficient agent RL, AstraFlow natively enables: 𝟐.𝟕× 𝐟𝐚𝐬𝐭𝐞𝐫 𝐦𝐮𝐥𝐭𝐢-𝐩𝐨𝐥𝐢𝐜𝐲 𝐚𝐠𝐞𝐧𝐭𝐬 𝐜𝐨𝐥𝐥𝐚𝐛𝐨𝐫𝐚𝐭𝐢𝐯𝐞 𝐑𝐋 𝐭𝐫𝐚𝐢𝐧𝐢𝐧𝐠 Achieves comparable or better accuracy than verl-based baseline. 𝐙𝐞𝐫𝐨-𝐜𝐨𝐝𝐞 𝐬𝐲𝐬𝐭𝐞𝐦 𝐟𝐥𝐞𝐱𝐢𝐛𝐢𝐥𝐢𝐭𝐲 Supports elastic multi-policy training and cross-region rollout across heterogeneous GPUs. ≤𝟏.𝟏% 𝐬𝐩𝐚𝐫𝐬𝐞 𝐭𝐫𝐚𝐧𝐬𝐟𝐞𝐫 𝐟𝐨𝐫 𝐫𝐞𝐦𝐨𝐭𝐞 𝐫𝐨𝐥𝐥𝐨𝐮𝐭 Same to @FireworksAI_HQ ’s sparse RL transfer design, AstraFlow cuts sync from ~28 GB to ~1.5 GB, with deltas ≤1.1% of weights, m

@InfiniAILab: We’re excited to release 𝐀𝐬𝐭𝐫𝐚𝐅𝐥𝐨𝐰, an open-source, dataflow-oriented RL system for training multi-agentic and multi-policy LLMs. Built for scalable, flexible, and efficient agent RL, AstraFlow natively enables: 𝟐.𝟕× 𝐟𝐚𝐬𝐭𝐞𝐫 𝐦𝐮𝐥𝐭𝐢-𝐩𝐨𝐥𝐢𝐜𝐲 𝐚𝐠𝐞𝐧𝐭𝐬 𝐜𝐨𝐥𝐥𝐚𝐛𝐨𝐫𝐚𝐭𝐢𝐯𝐞 𝐑𝐋 𝐭𝐫𝐚𝐢𝐧𝐢𝐧𝐠 Achieves comparable or better accuracy than verl-based baseline. 𝐙𝐞𝐫𝐨-𝐜𝐨𝐝𝐞 𝐬𝐲𝐬𝐭𝐞𝐦 𝐟𝐥𝐞𝐱𝐢𝐛𝐢𝐥𝐢𝐭𝐲 Supports elastic multi-policy training and cross-region rollout across heterogeneous GPUs. ≤𝟏.𝟏% 𝐬𝐩𝐚𝐫𝐬𝐞 𝐭𝐫𝐚𝐧𝐬𝐟𝐞𝐫…

saved by

• Christina Lee

related reading

• Sonya Huang 🐥 on X: "Today's Training Data episode takes us BTS on the infrastructure challenges required to do large RL runs at scale, featuring @ellev3n11 (Composer Lead at @cursor_ai) and @dzhulgakov (Co-Founder at @FireworksAI_HQ). The Cursor team trained Composer 2 on Fireworks by starting with https://t.co/6LLlJlyl8Q" / Xx.com
• Is Frontier Asynchronous RL Solved? — Luke J. Huangluk-huang.github.io
• LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
• Rethinking RL Infra for Agents | B'Logbillxbf.github.io
• Composer2.pdfcursor.com
• State of RL for reasoning LLMs | A. Weersaweers.de
• Forge: Scalable Agent RL Framework and Algorithm - MiniMax News | MiniMaxminimax.io
• Explore | alphaXivalphaxiv.org
• Building Effective AI Agents \ Anthropicanthropic.com
• Building Effective AI Agents \ Anthropicanthropic.com
• PostTrainBenchposttrainbench.com
• [2603.21972] Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipearxiv.org