Metraipolis › archive › dc_e3fd1be77d8a
From Proposal to Verified Effect: Praxa, an Evidence-Bound Harness for Governed AI Agent Execution — arXiv:2610.00015
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.00015
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:01:11.470Z
- SHA-256 of the archived text
34257b5d9ac4df91d9c74466b7cdbb44e789955737334a494e23df4b167a7fe0- Stable URL of this page
https://metraipolis.com/documento/dc_e3fd1be77d8a
How to cite
From Proposal to Verified Effect: Praxa, an Evidence-Bound Harness for Governed AI Agent Execution — arXiv:2610.00015 — arXiv (en), https://arxiv.org/abs/2610.00015 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e3fd1be77d8a (Metraipolis archive dc_e3fd1be77d8a, sha256 34257b5d9ac4df91d9c74466b7cdbb44e789955737334a494e23df4b167a7fe0)
BibTeX
@misc{dce3fd1be77d8a,
title = {From Proposal to Verified Effect: Praxa, an Evidence-Bound Harness for Governed AI Agent Execution — arXiv:2610.00015},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.00015},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e3fd1be77d8a; sha256 34257b5d9ac4df91d9c74466b7cdbb44e789955737334a494e23df4b167a7fe0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00015. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large-language-model agents can propose and execute actions, but proposal, authority, dispatch, verified external effect, and serving promotion are different claims. We present Praxa, an agent harness that represents these states explicitly through deterministic admission, brokered execution, external read-back, reconciliation, and reviewed promotion. We report four evidence lanes. First, an author-run repository-local audit at a pinned revision passed 1,027/1,027 unit tests and 89/89 Workerd tests, instrumented all 363 expected source files, and met four coverage floors; raw per-test transcripts and independent reproduction are unavailable. Second, in a provider-backed Terminal-Bench Core 0.1.1 pilot across 12 curated tasks, baseline and reliability-layer arms each passed 17/36 strict trials. The reliability layer used 37.49% more input and 50.73% more output tokens, so the pilot does not support superiority. Third, in a post-debug, two-order coordination-proxy development comparison, baseline and a source-authored candidate each completed 180/180 trials with equal measured accuracy, full hermetic crash recovery, and zero protected violations. The candidate used 37.11% fewer tokens, 33.84% lower estimated endpoint cost, and 11.63% fewer steps; this does not establish improved quality, latency, or production behavior. Fourth, deployed source/configuration evidence shows bounded reflection, recall accounting, memory compilation, and tool-health paths, but no production outcome lift. Praxa's supported contribution is an evidence-bound architecture that makes authority-to-effect transitions explicit and testable. Current evidence does not establish adversarial security, production safety, general specialist superiority, autonomous recursive optimization, or user benefit. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.00015 — 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 2026-10-06T10:21:27.833Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).