T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks
T1, a 122B MoE terminal agent trained with reinforcement learning, reaches 64.0% on Terminal-Bench 2.1, surpassing GPT-5.4 and GLM-5.1 on long-horizon tasks.
55
- Mentions · 7d0
- Mentions · 30d0
- All mentions1
- First seenSep 9, 2026
- Last mentionedSep 9, 2026
Timeline
1 articles · newest firstAppears with
- Terminal-Benchproduct · 1
- GPT-5.4ai model · 1
- GLM-5.1ai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.