{"slug": "t1-terminal-agent-reinforcement-learning-for-long-horizon-tasks", "title": "T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks", "summary": "A Mixture-of-Experts model called T1, with 122B total parameters, has been trained with reinforcement learning to operate a real shell in a cloud sandbox for up to 300+ tool calls on long-horizon terminal tasks such as coding and scientific discovery. The model targets terminal agent reinforcement learning, a capability the source frames as increasingly important as agent usage shifts toward long-horizon work.", "body_md": "Agent usage is shifting toward long-horizon tasks such as coding and scientific discovery, among which terminal tasks are especially important. We introduce T1, a Mixture-of-Experts model of 122B total trained with reinforcement learning, operating a real shell in a cloud sandbox for up to 300+ tool", "url": "https://wpnews.pro/news/t1-terminal-agent-reinforcement-learning-for-long-horizon-tasks", "canonical_source": "https://aiflash.com/news/117367/", "published_at": "2026-09-11 01:30:12+00:00", "updated_at": "2026-09-11 01:52:46.509960+00:00", "lang": "en", "topics": ["ai-agents", "ai-research", "large-language-models", "developer-tools"], "entities": ["T1"], "alternates": {"html": "https://wpnews.pro/news/t1-terminal-agent-reinforcement-learning-for-long-horizon-tasks", "markdown": "https://wpnews.pro/news/t1-terminal-agent-reinforcement-learning-for-long-horizon-tasks.md", "text": "https://wpnews.pro/news/t1-terminal-agent-reinforcement-learning-for-long-horizon-tasks.txt", "jsonld": "https://wpnews.pro/news/t1-terminal-agent-reinforcement-learning-for-long-horizon-tasks.jsonld"}}