From Proposal to Verified Effect: Praxa, an Evidence-Bound Harness for Governed AI Agent Execution

Praxa, an evidence-bound agent harness that makes authority-to-effect transitions explicit through deterministic admission, brokered execution, external read-back, reconciliation, and reviewed promotion, reports four evidence lanes in arXiv:2610.00015v1, with its provider-backed Terminal-Bench Core 0.1.1 pilot across 12 curated tasks showing baseline and reliability-layer arms each passing 17/36 strict trials while the reliability layer consumed 37.49% more input and 50.73% more output tokens, so the pilot does not support superiority. A post-debug, two-order coordination-proxy development comparison found baseline and a source-authored candidate each completed 180/180 trials with equal measured accuracy, full hermetic crash recovery, and zero protected violations, with the candidate using 37.11% fewer tokens, 33.84% lower estimated endpoint cost, and 11.63% fewer steps, though this does not establish improved quality, latency, or production behavior. The authors state Praxa's supported contribution is an evidence-bound architecture that makes authority-to-effect transitions explicit and testable, and that current evidence does not establish adversarial security, production safety, general specialist superiority, autonomous recursive optimization, or user benefit.

arXiv:2610.00015v1 Announce Type: new Abstract: 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.