FRIDAY 11 SEPTEMBER 2026 latent·wire 108 PIECES ON FILE
← All subjects Subject · Models

T1 Terminal Agent RL

Covered by
arxiv.org

Timeline

  1. T1 trains a 122B Mixture-of-Experts terminal agent with RL across 300-turn tasks

    T1 is a rare full training recipe, not just a model card, for reinforcement learning that survives hundreds of shell turns, and its disjoint from Terminal-Bench 2.1 is the test of whether such gains are real capability or benchmark memorization.

    1 source · excerpt-only, thin-sourcing

All sources (1)

  1. arXiv cs.LG2026-09-11

Related subjects