Views
No views yet

[!NOTE] For full information, go check out the Tmax paper here.
| Model | TB Lite | TB 2.1 |
|---|---|---|
| Qwen 3 8B | 7.3 +/- 1.0 | 1.1 +/- 0.9 |
| Tmax SFT 8B | 11.5 +/- 0.1 | 6.0 +/- 1.4 |
| Tmax 8B | 17.7 +/- 1.9 | 5.2 +/- 2.3 |
1uvx vllm==0.19.1 serve allenai/tmax-8b \
2 --served-model-name tmax-8b \
3 --enable-auto-tool-choice \
4 --tool-call-parser qwen3_xml \
5 --port 8008 \
6 --max-model-len 40960 \
7 --tensor-parallel-size 8 \
8 --language_model_onlylanguage_model_only as we removed the vision head during training.@misc{ivison2026tmaxsimplerecipeterminal,
title={Tmax: A simple recipe for terminal agents},
author={Hamish Ivison and Junjie Oscar Yin and Rulin Shao and Teng Xiao and Nathan Lambert and Hannaneh Hajishirzi},
year={2026},
eprint={2606.23321},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2606.23321},
}