# MIRROR paper defends multi-agent systems against agent-in-the-middle tampering as harnesses hand routing and injection checks to fast single-pass models

A companion arXiv study audits the single-pass "System-1" models that harnesses use to choose tools and flag injected instructions. OpenAI announced a Decisions API for this same layer of bounded decisions at its DevDay event.

- Published: 2026-10-05T06:00:43.302Z
- Canonical: https://polylog.news/ai/2026-10-05/mirror-paper-defends-multi-agent-systems-against-agent-in-th
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv cs.CR (MIRROR)](https://arxiv.org/abs/2610.02349), [arXiv cs.AI (Fast Models, Slow Evidence)](https://arxiv.org/abs/2610.02267), [AI Weekly](https://aiweekly.co/ai-news-today/edition/2026-10-01)

Multi-agent LLM systems pass messages between agents. Those messages form an attack surface that current defenses largely ignore. That is the argument of MIRROR: Multipath Quorum Integrity for LLM Multi-Agent Communication, posted to arXiv…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-05/mirror-paper-defends-multi-agent-systems-against-agent-in-th (subscription information: https://polylog.news/pricing).