返回首页
arXiv AI··论文与技术

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

中文摘要

Praxa通过确定性准入和验证机制,确保AI智能体执行过程的透明性、权威性及效果可验证,提升了智能体决策的可靠性。

English Summary

Praxa is a harness ensuring AI agent reliability through deterministic admission, brokered execution, and verified external effects, bridging the gap between proposal and confirmed action.

原文节选

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 v…