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.
T1 is a 122B mixture-of-experts model trained with reinforcement learning to operate a real shell in a cloud sandbox for up to 300+ tool-call turns per task, rewarded by executing each task's own verifier. The recipe combines aggressive warm starts, dense process rewards, TITO construction, and rollout routing replay, cutting the training-to-inference log-probability difference from 0.021 to 0.013 with zero token drift. Training used an out-of-distribution corpus disjoint from Terminal-Bench 2.1. Post-training raised the base model from 43.8% to 64.0% resolved on Terminal-Bench 2.1 and 27.9% on Long-Horizon Terminal Bench.
- RL-trained 122B MoE agent operates real shells for 300+ tool-call turns
- TITO construction and rollout routing replay cut log-probability drift to 0.013
- 43.8% to 64.0% resolved on Terminal-Bench 2.1 after post-training
- 27.9% on Long-Horizon Terminal Bench, surpassing GPT-5.4 and GLM-5.1
- Out-of-distribution training corpus avoids benchmark overfitting
- Tags
- agentic-ailong-horizon-tasksmixture-of-expertsreinforcement-learningterminal-agentsterminal-bench
- Products
- Terminal-Bench
From the original article
1 min read at huggingface.co
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.
By Junyao Yang, Yucheng Shi, Zhongzhi Li · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.