--- format: "aidr-story-markdown/v1" id: "19f6ff11610d0423f230848eb322795bffa062b3779ee440ab66e82b7b09fb53" canonical_url: "https://aidr.today/19f6ff11?lang=en" title: "Burtenshaw Launches Agent RL Design Platform for Qwen-3.8-27B" lang: "en" requested_lang: "en" available_langs: ["en","vi"] translation_fallback: null fallback_fields: [] published_at: "2026-10-08T14:41:50.000Z" category: "Tools" topics: ["agent","devtools"] source_urls: ["https://marketbrief.now/ai/burtenshaw-launches-agent-rl-design-platform-for-qwen-38-27b-5c3dfd06","https://huggingnews.com/ai/burtenshaw-launches-agent-rl-design-platform-for-qwen-38-27b-5c3dfd06"] summary: "Ben Burtenshaw launched Open Env Arena, a platform where AI agents compete to design reinforcement learning environments used to train the Qwen-3.8-27B model, with results posted to a public leaderboard. The platform runs on GPUs from Nebius AI and PostTrainArena from Benchflow AI, and will expand to domain-specific arenas after the initial round is evaluated against public benchmarks." --- # Burtenshaw Launches Agent RL Design Platform for Qwen\-3\.8\-27B > [Open the canonical story]() **Published:** 2026-10-08T14:41:50.000Z **Category:** Tools **Topics:** agent, devtools ## Summary Ben Burtenshaw launched Open Env Arena, a platform where AI agents compete to design reinforcement learning environments used to train the Qwen\-3\.8\-27B model, with results posted to a public leaderboard\. The platform runs on GPUs from Nebius AI and PostTrainArena from Benchflow AI, and will expand to domain\-specific arenas after the initial round is evaluated against public benchmarks\. ## Sources - [Story source]() - [Story source]()