{
  "id": 14823,
  "url": "https://arxiv.org/abs/2607.26773v1",
  "title": "Do Latent Channels Actually Communicate? A Causal Audit of Latent Multi-Agent LLM",
  "summary": "Latent communication in large language model (LLM)-based multi-agent systems (MAS) transmits continuous internal representations instead of text, but greater representational capacity does not establish that the receiver uses task-relevant information. End-task performance alone also cannot reveal whether an observed effect depends on message presence, content generated for the evaluated example, or information supplied by a separate agent. We introduce a causal audit that applies controlled mes",
  "authors": "Huixiang Zhang, Mahzabeen Emu",
  "category": "research",
  "topics": "agents-autonomy,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-29T11:14:27.000Z",
  "fetched_at": "2026-07-30T05:10:24.387Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/14823",
  "original_url": "https://arxiv.org/abs/2607.26773v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}