Metraipolis › archive › dc_177d40693ec7
Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning — arXiv:2608.16620
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.16620
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T18:07:22.000Z
- SHA-256 of the archived text
d91391f5b4a5cf929394f4fdf25ce560dd2f5d759081c0f408af54a5178fb552- Stable URL of this page
https://metraipolis.com/documento/dc_177d40693ec7
How to cite
Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning — arXiv:2608.16620 — arXiv (en), https://arxiv.org/abs/2608.16620 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_177d40693ec7 (Metraipolis archive dc_177d40693ec7, sha256 d91391f5b4a5cf929394f4fdf25ce560dd2f5d759081c0f408af54a5178fb552)
BibTeX
@misc{dc177d40693ec7,
title = {Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning — arXiv:2608.16620},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.16620},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_177d40693ec7; sha256 d91391f5b4a5cf929394f4fdf25ce560dd2f5d759081c0f408af54a5178fb552},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16620. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Palmyra x6 is a large language model optimized for use with enterprise-oriented agentic tasks. The model was built by post-training a Mixture-of-Experts base model with Anchored Supervised Fine-Tuning on a compact corpus of verified, synthetic tool-use trajectories, optimized with a Muon + Adam hybrid. The recipe is deliberately conservative and deliberately controlled: 626 trajectories, a single epoch, a low learning rate, and a KL anchor to the frozen base. The model shows substantial gains over the previous default model for Writer Agent, and compares favorably with several recent models on public benchmarks, scoring the highest on BFCL Core at $0.785$ and posts the highest six-benchmark mean of the cohort. Furthermore, the model has shown itself to be competitive or leading relative to comparators in our bias and safety evaluations. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.16620 — 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 2026-10-18T16:29:14.131Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).