T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks
Quick summary
arXiv:2609.11042v1 Announce Type: cross Abstract: 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-call turns per task, rewarded by executing each task's own verifier. We provide a comprehensive recipe: First, an aggressively warm-started to stabilize actor-critic training, with a dense process reward scoring trajectories by the absolute number o
Key takeaways
- arXiv:2609.11042v1 Announce Type: cross Abstract: 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-call turns per task, rewarded by executing each task's own verifier.
- We provide a comprehensive recipe: First, an aggressively warm-started to stabilize actor-critic training, with a dense process reward scoring trajectories by the absolute number o
Why it matters
“T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks” shows why AI risk cannot be reduced to answer accuracy. Access controls, logging, human approval and incident response need to be designed into the workflow from the start.
Member comments