# Paper Shows Tool Use Lets Multi-Agent LLMs Collude Through Undetectable Steganography

Monitoring plain-text communication between agents may not catch secret coordination once those agents can call tools.

- Published: 2026-06-30T10:59:35.888Z
- Canonical: https://polylog.news/ai/2026-06-30/paper-shows-tool-use-lets-multi-agent-llms-collude-through-u
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv cs.CR](https://arxiv.org/abs/2606.28425), [arXiv cs.CR (security survey)](https://arxiv.org/abs/2606.28450)

A new paper, Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems, targets a defense that many agent-safety designs rely on: monitoring the plain-text messages that agents exchange. The authors argue that once agents can c…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-06-30/paper-shows-tool-use-lets-multi-agent-llms-collude-through-u (subscription information: https://polylog.news/pricing).