# Two Papers Try to Make Agent Authority Auditable Before Self-Evolving Agents Reach Production

One proposes a harness that separates proposing an action from proving its external effect, the other maps how safety properties break when agents keep rewriting their own memories, tools and skills.

- Published: 2026-10-02T06:31:19.109Z
- Canonical: https://polylog.news/ai/2026-10-02/two-papers-try-to-make-agent-authority-auditable-before-self
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv cs.AI](https://arxiv.org/abs/2610.00015), [arXiv cs.CR](https://arxiv.org/abs/2610.00093)

Agent frameworks generally treat a tool call and its consequence as one event. Praxa, described in a new paper, argues that proposal, authority, dispatch, verified external effect and promotion to serving are five separate claims that deser…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-02/two-papers-try-to-make-agent-authority-auditable-before-self (subscription information: https://polylog.news/pricing).