Metraipolis › archive › dc_4b1ef25ecfd2
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents — arXiv:2609.39982
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39982
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T12:39:45.566Z
- SHA-256 of the archived text
6546c4735528ccb88dc4dc5163bce35630dbb0f33d198bb064f6659fa6c2f112- Stable URL of this page
https://metraipolis.com/documento/dc_4b1ef25ecfd2
How to cite
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents — arXiv:2609.39982 — arXiv (en), https://arxiv.org/abs/2609.39982 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4b1ef25ecfd2 (Metraipolis archive dc_4b1ef25ecfd2, sha256 6546c4735528ccb88dc4dc5163bce35630dbb0f33d198bb064f6659fa6c2f112)
BibTeX
@misc{dc4b1ef25ecfd2,
title = {Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents — arXiv:2609.39982},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39982},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4b1ef25ecfd2; sha256 6546c4735528ccb88dc4dc5163bce35630dbb0f33d198bb064f6659fa6c2f112},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39982. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Terminal agents act through stochastic model generations, yet the ability to generate a useful action does not ensure its reliable execution. A poor command (e.g., wrong package install) can change the environment in ways that hinder subsequent progress, even when the model could generate a better alternative. We investigate whether allocating test-time compute at the model-harness boundary can improve action reliability and trajectory success, and what makes this allocation effective. To study these questions, we introduce Mid-Harness, which samples and verifies candidate actions before forwarding one for execution, while keeping the generator and harness unchanged. With a TMAX-9B generator, more action sampling yields little benefit under weak verification, whereas a capable verifier can exploit useful alternatives from the same generator. On TerminalBench-Lite, a GPT-5.6 Sol verifier raises Pass@1 from 50.00% for the base agent to 68.03% with 8 sampled actions. When the same TMAX-9B model serves as the verifier, pairwise verification performs best among the evaluated verification mechanisms. Distilling responses from the stronger verifier into TMAX-9B further improves Pass@1, while leaving the action generator unchanged. With TMAX-9B on TerminalBench-Lite, combining action and trajectory scaling reaches higher success at lower estimated token cost than generating more trajectories alone. Mid-Harness also improves performance across additional models, benchmarks, and harnesses. These findings identify action scaling as a promising target for test-time compute scaling in terminal agents. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.MA). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2609.39982 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T12:12:18.665Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).