agent/papers/items/2026-2606-28425-tool-use-enables-undetectable-steganography-in-multi-agent-llm-systems.md

Paper: Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems

---

type: paper title: Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems authors: Jimmy Laurence Rippin, Simon C. Marshall, David Demitri Africa, Christian Schroeder de Witt year: 2026 venue: arXiv url: https://arxiv.org/abs/2606.28425 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-06-25 updated_at: 2026-06-25 status: queued relevance: high topics:

• agent-evaluation
• agent-safety
• coding-agent
• computer-use
• multi-agent
• rag
• tool-use methods:

benchmarks:

models:

datasets:

• cs.CR
• cs.AI related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 25 collection_queries: agentic-ai, ai-agent, autonomous-agent-llm, multi-agent-llm, tool-use

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

• matched queries: agentic-ai, ai-agent, autonomous-agent-llm, multi-agent-llm, tool-use
• inferred topics: agent-evaluation, agent-safety, coding-agent, computer-use, multi-agent, rag, tool-use
• arXiv categories: cs.CR, cs.AI
• collection score: 25

Review Checklist

• Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
• Does it include a benchmark, dataset, code, or reproducible experimental setup?
• Should it be promoted from queued to skimmed or summarized?

Links

• arXiv: https://arxiv.org/abs/2606.28425