{
  "id": 16930,
  "url": "https://arxiv.org/abs/2608.04893v1",
  "title": "When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs",
  "summary": "Multi-agent LLM systems relay key--value caches instead of text and credit their gains to exchanged ``latent thoughts''. That credit is a claim about \\emph{which} example's cache is relayed, not merely that one is. We audit it causally in released systems. The cache is replaced with deranged (mismatched-example), zeroed, and moment-matched random counterparts, under two regimes defined by whether the receiver needs the sender's private information. Where it does, the battery reads ceiling: 100\\%",
  "authors": "Jiaming Cheng, Subhransu Das, Rajiv Ramnath",
  "category": "research",
  "topics": "agents-autonomy,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-05T14:18:42.000Z",
  "fetched_at": "2026-08-06T05:10:11.148Z",
  "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/16930",
  "original_url": "https://arxiv.org/abs/2608.04893v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}